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

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

Neuron 1314 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1119949 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1032316 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0151. Min Act: -0.0006

Data Index: 802616 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1482290 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0006

Data Index: 45630 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0148. Min Act: -0.0006

Data Index: 646302 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0129. Min Act: -0.0006

Data Index: 485157 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0153. Min Act: -0.0006

Data Index: 419295 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0143. Min Act: -0.0006

Data Index: 942635 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1231440 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0147. Min Act: -0.0006

Data Index: 605529 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1082093 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1251829 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1080504 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0126. Min Act: -0.0006

Data Index: 259437 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1286320 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0124. Min Act: -0.0006

Data Index: 33213 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0138. Min Act: -0.0006

Data Index: 106478 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1275236 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0117. Min Act: -0.0006

Data Index: 188953 (C4 (Web Text))

Max Activating Token Index: 309