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

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

Neuron 1763 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0003

Data Index: 789849 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0198. Min Act: -0.0003

Data Index: 976709 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1211592 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0187. Min Act: -0.0003

Data Index: 129896 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1065981 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0189. Min Act: -0.0003

Data Index: 801484 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0187. Min Act: -0.0003

Data Index: 853004 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0179. Min Act: -0.0003

Data Index: 421594 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0003

Data Index: 585825 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0173. Min Act: -0.0003

Data Index: 728762 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0179. Min Act: -0.0003

Data Index: 123946 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1338516 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1235608 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0162. Min Act: -0.0003

Data Index: 934975 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0162. Min Act: -0.0003

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1084769 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0155. Min Act: -0.0003

Data Index: 385386 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0157. Min Act: -0.0004

Data Index: 1564148 (Python Code)

Max Activating Token Index: 777

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1291596 (C4 (Web Text))

Max Activating Token Index: 849