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

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

Neuron 1003 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0006

Data Index: 37425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0158. Min Act: -0.0006

Data Index: 387917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1321383 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0006

Data Index: 353477 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0006

Data Index: 713813 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0006

Data Index: 600262 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0006

Data Index: 887499 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1204217 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1028993 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0006

Data Index: 202032 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0134. Min Act: -0.0006

Data Index: 461442 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0006

Data Index: 284868 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0135. Min Act: -0.0006

Data Index: 513205 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1189297 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1024548 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0135. Min Act: -0.0006

Data Index: 306463 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0131. Min Act: -0.0006

Data Index: 408886 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1284188 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0131. Min Act: -0.0006

Data Index: 137437 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0133. Min Act: -0.0006

Data Index: 77354 (C4 (Web Text))

Max Activating Token Index: 497