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

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

Neuron 5692 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0271. Min Range: -4.0271

Max Act: 4.0271. Min Act: -0.0000

Data Index: 711235 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.8711. Min Act: -0.0000

Data Index: 81373 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 4.0271. Min Range: -4.0271

Max Act: 4.0251. Min Act: -0.0000

Data Index: 1104974 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.5050. Min Act: -0.0000

Data Index: 82017 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.2630. Min Act: -0.0000

Data Index: 657166 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.4104. Min Act: -0.0000

Data Index: 813149 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.0753. Min Act: -0.0000

Data Index: 482748 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.3147. Min Act: -0.0000

Data Index: 1150198 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.2892. Min Act: -0.0000

Data Index: 1100089 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.4099. Min Act: -0.0000

Data Index: 262214 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.2590. Min Act: 0.0000

Data Index: 1256957 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.2152. Min Act: -0.0000

Data Index: 1054886 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.0544. Min Act: -0.0000

Data Index: 357292 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.2004. Min Act: -0.0000

Data Index: 451251 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1821. Min Act: -0.0000

Data Index: 1321985 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1740. Min Act: -0.0000

Data Index: 861703 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1813. Min Act: 0.0000

Data Index: 690832 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1755. Min Act: -0.0000

Data Index: 480527 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1693. Min Act: 0.0000

Data Index: 851079 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 4.0271. Min Range: -4.0271

Max Act: 3.1714. Min Act: -0.0000

Data Index: 970336 (C4 (Web Text))

Max Activating Token Index: 287