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

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

Neuron 1663 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: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0006

Data Index: 966509 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0143. Min Act: -0.0006

Data Index: 222938 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0006

Data Index: 401177 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1083601 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0124. Min Act: -0.0006

Data Index: 829159 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0125. Min Act: -0.0006

Data Index: 246810 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0122. Min Act: -0.0006

Data Index: 857522 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1281217 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0121. Min Act: -0.0006

Data Index: 456538 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1172398 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0117. Min Act: -0.0006

Data Index: 169262 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0114. Min Act: -0.0006

Data Index: 708415 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0117. Min Act: -0.0006

Data Index: 378630 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1304922 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0111. Min Act: -0.0006

Data Index: 916082 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1281816 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0113. Min Act: -0.0006

Data Index: 810857 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0115. Min Act: -0.0006

Data Index: 716188 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0107. Min Act: -0.0006

Data Index: 66990 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0112. Min Act: -0.0006

Data Index: 160486 (C4 (Web Text))

Max Activating Token Index: 154