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

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

Neuron 263 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.6467. Min Act: -0.1700

Data Index: 858079 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.6154. Min Act: -0.1700

Data Index: 1323617 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5528. Min Act: -0.1700

Data Index: 1257048 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5528. Min Act: -0.1700

Data Index: 418525 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 801121 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 230374 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 907529 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1344523 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1064389 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 735973 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4901. Min Act: -0.1700

Data Index: 757037 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1083204 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.5215. Min Act: -0.1700

Data Index: 413521 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1211205 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4588. Min Act: -0.1700

Data Index: 636990 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4588. Min Act: -0.1700

Data Index: 86965 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4274. Min Act: -0.1700

Data Index: 741875 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4118. Min Act: -0.1700

Data Index: 1016239 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4118. Min Act: -0.1700

Data Index: 612221 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.6467. Min Range: -3.6467

Max Act: 3.4274. Min Act: -0.1700

Data Index: 1202525 (C4 (Web Text))

Max Activating Token Index: 880