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

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

Neuron 579 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: 0.0226. Min Range: -0.0226

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1281561 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0001

Data Index: 97108 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0212. Min Act: -0.0001

Data Index: 554708 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0187. Min Act: -0.0001

Data Index: 510371 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0189. Min Act: -0.0001

Data Index: 610407 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0204. Min Act: -0.0002

Data Index: 462554 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0001

Data Index: 498087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1001183 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0179. Min Act: -0.0001

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0001

Data Index: 938881 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0176. Min Act: -0.0001

Data Index: 512393 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1272440 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0172. Min Act: -0.0001

Data Index: 613138 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1246666 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0157. Min Act: -0.0001

Data Index: 682333 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0146. Min Act: -0.0001

Data Index: 46239 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0159. Min Act: -0.0001

Data Index: 797948 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0141. Min Act: -0.0001

Data Index: 20751 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0120. Min Act: -0.0001

Data Index: 761600 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0142. Min Act: -0.0002

Data Index: 309889 (C4 (Web Text))

Max Activating Token Index: 112