Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0000

Data Index: 865102 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0189. Min Act: -0.0000

Data Index: 14289 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1507803 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0188. Min Act: -0.0000

Data Index: 524812 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0174. Min Act: -0.0001

Data Index: 206423 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1484285 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0189. Min Act: -0.0001

Data Index: 897160 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1396328 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0167. Min Act: -0.0001

Data Index: 431805 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0178. Min Act: -0.0001

Data Index: 57168 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0175. Min Act: -0.0001

Data Index: 604646 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0156. Min Act: -0.0001

Data Index: 494062 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0170. Min Act: -0.0001

Data Index: 451840 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0167. Min Act: -0.0001

Data Index: 968733 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1136575 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0187. Min Act: -0.0001

Data Index: 628624 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0165. Min Act: -0.0000

Data Index: 184268 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0163. Min Act: -0.0000

Data Index: 1652880 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1133050 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1062526 (C4 (Web Text))

Max Activating Token Index: 550