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

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

Neuron 4738 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.8260. Min Act: -0.0000

Data Index: 131658 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1655546 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1191588 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.6408. Min Act: -0.0000

Data Index: 817708 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1079538 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1182214 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1072547 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5076. Min Act: -0.0000

Data Index: 244630 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4964. Min Act: -0.0000

Data Index: 418916 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1240043 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.5086. Min Act: -0.0000

Data Index: 643119 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4798. Min Act: -0.0000

Data Index: 610710 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4922. Min Act: -0.0000

Data Index: 756338 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1306001 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4567. Min Act: -0.0000

Data Index: 628005 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1393908 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4585. Min Act: -0.0000

Data Index: 6453 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4387. Min Act: -0.0000

Data Index: 730895 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4371. Min Act: -0.0000

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.8260. Min Range: -0.8260

Max Act: 0.4362. Min Act: -0.0000

Data Index: 704506 (C4 (Web Text))

Max Activating Token Index: 371