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

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

Neuron 1845 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: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0006

Data Index: 490368 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0169. Min Act: -0.0006

Data Index: 187538 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0166. Min Act: -0.0006

Data Index: 829058 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0164. Min Act: -0.0006

Data Index: 381831 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1076045 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1571519 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0158. Min Act: -0.0006

Data Index: 253940 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0154. Min Act: -0.0006

Data Index: 251414 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1285134 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0146. Min Act: -0.0006

Data Index: 855481 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0148. Min Act: -0.0006

Data Index: 844462 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0141. Min Act: -0.0006

Data Index: 797438 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1595522 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1619054 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0145. Min Act: -0.0006

Data Index: 794195 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0148. Min Act: -0.0006

Data Index: 272883 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0144. Min Act: -0.0006

Data Index: 976023 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0144. Min Act: -0.0006

Data Index: 151103 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1594562 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1422294 (Python Code)

Max Activating Token Index: 831