Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1881 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0002

Data Index: 887755 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0179. Min Act: -0.0001

Data Index: 121963 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0170. Min Act: -0.0001

Data Index: 339244 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0176. Min Act: -0.0001

Data Index: 141526 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0165. Min Act: -0.0002

Data Index: 569783 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0165. Min Act: -0.0002

Data Index: 575013 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0160. Min Act: -0.0002

Data Index: 43919 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0157. Min Act: -0.0002

Data Index: 714386 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1106394 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0159. Min Act: -0.0002

Data Index: 985264 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0152. Min Act: -0.0001

Data Index: 228276 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0152. Min Act: -0.0002

Data Index: 700293 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0148. Min Act: -0.0002

Data Index: 522427 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0153. Min Act: -0.0002

Data Index: 937391 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0145. Min Act: -0.0002

Data Index: 541559 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0134. Min Act: -0.0001

Data Index: 35735 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0146. Min Act: -0.0001

Data Index: 555180 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0150. Min Act: -0.0002

Data Index: 319446 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1082076 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0157. Min Act: -0.0002

Data Index: 489213 (C4 (Web Text))

Max Activating Token Index: 283