< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 382 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.6263. Min Act: -0.1700

Data Index: 721920 (C4 (Web Text))

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.5013. Min Act: -0.1700

Data Index: 1022664 (C4 (Web Text))

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.0950. Min Act: -0.1700

Data Index: 1089521 (C4 (Web Text))

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.2513. Min Act: -0.1700

Data Index: 33261 (C4 (Web Text))

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.0638. Min Act: -0.1700

Data Index: 399747 (C4 (Web Text))

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.6263. Min Range: -6.6263

Max Act: 6.0013. Min Act: -0.1700

Data Index: 1104656 (C4 (Web Text))

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.9388. Min Act: -0.1700

Data Index: 1399687 (Python Code)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.9700. Min Act: -0.1700

Data Index: 749848 (C4 (Web Text))

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.9700. Min Act: -0.1700

Data Index: 667273 (C4 (Web Text))

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.9388. Min Act: -0.1700

Data Index: 590532 (C4 (Web Text))

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.9075. Min Act: -0.1700

Data Index: 48678 (C4 (Web Text))

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.8763. Min Act: -0.1700

Data Index: 695598 (C4 (Web Text))

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.8450. Min Act: -0.1700

Data Index: 1059372 (C4 (Web Text))

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.8450. Min Act: -0.1700

Data Index: 1311495 (C4 (Web Text))

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.8138. Min Act: -0.1700

Data Index: 1283601 (C4 (Web Text))

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.6575. Min Act: -0.1700

Data Index: 222096 (C4 (Web Text))

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.7825. Min Act: -0.1700

Data Index: 1555612 (Python Code)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.7825. Min Act: -0.1700

Data Index: 1061796 (C4 (Web Text))

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.7513. Min Act: -0.1700

Data Index: 380153 (C4 (Web Text))

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.6263. Min Range: -6.6263

Max Act: 5.8138. Min Act: -0.1700

Data Index: 186974 (C4 (Web Text))

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #19