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

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

Neuron 657 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0006

Data Index: 658889 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0006

Data Index: 605913 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0136. Min Act: -0.0006

Data Index: 274247 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1167543 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0006

Data Index: 367562 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0122. Min Act: -0.0006

Data Index: 947861 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0122. Min Act: -0.0006

Data Index: 120082 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0115. Min Act: -0.0006

Data Index: 325434 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0006

Data Index: 755846 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0123. Min Act: -0.0006

Data Index: 218353 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0119. Min Act: -0.0006

Data Index: 93157 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0119. Min Act: -0.0006

Data Index: 450217 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0121. Min Act: -0.0006

Data Index: 624027 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0121. Min Act: -0.0006

Data Index: 685725 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0117. Min Act: -0.0006

Data Index: 203754 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0111. Min Act: -0.0006

Data Index: 164254 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0120. Min Act: -0.0006

Data Index: 416300 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0113. Min Act: -0.0006

Data Index: 89633 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1012352 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1313107 (C4 (Web Text))

Max Activating Token Index: 467