< Prev | Home | Model | Random | Next >

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

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

Neuron 543 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1688. Min Range: -3.1688

Max Act: 3.1688. Min Act: -0.1700

Data Index: 692423 (C4 (Web Text))

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9795. Min Act: -0.1700

Data Index: 605964 (C4 (Web Text))

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9637. Min Act: -0.1700

Data Index: 1412100 (Python Code)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9637. Min Act: -0.1700

Data Index: 461195 (C4 (Web Text))

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9478. Min Act: -0.1700

Data Index: 845738 (C4 (Web Text))

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9637. Min Act: -0.1700

Data Index: 1151266 (C4 (Web Text))

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9478. Min Act: -0.1700

Data Index: 625470 (C4 (Web Text))

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9478. Min Act: -0.1700

Data Index: 909473 (C4 (Web Text))

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9320. Min Act: -0.1700

Data Index: 188738 (C4 (Web Text))

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9478. Min Act: -0.1700

Data Index: 1250995 (C4 (Web Text))

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9162. Min Act: -0.1700

Data Index: 1176596 (C4 (Web Text))

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9003. Min Act: -0.1700

Data Index: 1089943 (C4 (Web Text))

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.8844. Min Act: -0.1700

Data Index: 559782 (C4 (Web Text))

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9162. Min Act: -0.1700

Data Index: 553529 (C4 (Web Text))

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9003. Min Act: -0.1700

Data Index: 467055 (C4 (Web Text))

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9003. Min Act: -0.1700

Data Index: 333455 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.9003. Min Act: -0.1700

Data Index: 832765 (C4 (Web Text))

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.8844. Min Act: -0.1700

Data Index: 1413200 (Python Code)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.8844. Min Act: -0.1700

Data Index: 1380664 (Python Code)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1688. Min Range: -3.1688

Max Act: 2.8844. Min Act: -0.1700

Data Index: 198219 (C4 (Web Text))

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #19