Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0002

Data Index: 113222 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1229932 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0144. Min Act: -0.0002

Data Index: 210730 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1240776 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0141. Min Act: -0.0002

Data Index: 22350 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1162555 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0137. Min Act: -0.0002

Data Index: 953453 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0128. Min Act: -0.0002

Data Index: 89797 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0139. Min Act: -0.0002

Data Index: 834614 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0134. Min Act: -0.0002

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0127. Min Act: -0.0002

Data Index: 69299 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0139. Min Act: -0.0002

Data Index: 419775 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0136. Min Act: -0.0002

Data Index: 322486 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1448981 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0135. Min Act: -0.0002

Data Index: 868958 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0127. Min Act: -0.0002

Data Index: 852243 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0121. Min Act: -0.0002

Data Index: 721276 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1264689 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1003571 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0125. Min Act: -0.0002

Data Index: 353868 (C4 (Web Text))

Max Activating Token Index: 590