< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1831 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.6303. Min Act: -0.0928

Data Index: 108786 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5821. Min Act: -0.0928

Data Index: 340247 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5175. Min Act: -0.0830

Data Index: 219005 (C4 (Web Text))

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5337. Min Act: -0.1236

Data Index: 777265 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5013. Min Act: -0.0667

Data Index: 676782 (C4 (Web Text))

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5013. Min Act: -0.1060

Data Index: 688644 (C4 (Web Text))

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.5013. Min Act: -0.0977

Data Index: 393034 (C4 (Web Text))

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4851. Min Act: -0.0989

Data Index: 1000633 (C4 (Web Text))

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4851. Min Act: -0.0398

Data Index: 1012404 (C4 (Web Text))

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4851. Min Act: -0.0637

Data Index: 757217 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4689. Min Act: -0.0537

Data Index: 112110 (C4 (Web Text))

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4689. Min Act: -0.1397

Data Index: 199438 (C4 (Web Text))

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4851. Min Act: -0.0704

Data Index: 1260374 (C4 (Web Text))

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4526. Min Act: -0.0372

Data Index: 1362437 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4526. Min Act: -0.0464

Data Index: 1444275 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4364. Min Act: -0.0915

Data Index: 456218 (C4 (Web Text))

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4364. Min Act: -0.0682

Data Index: 100871 (C4 (Web Text))

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4526. Min Act: -0.0876

Data Index: 59151 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4526. Min Act: -0.0890

Data Index: 1165142 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6303. Min Range: -2.6303

Max Act: 2.4526. Min Act: -0.1001

Data Index: 217449 (C4 (Web Text))

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19