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

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

Neuron 5853 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: 1.5718. Min Range: -1.5718

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1231808 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1332431 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1056524 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.6636. Min Act: -0.0000

Data Index: 857083 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5695. Min Act: -0.0000

Data Index: 919379 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5593. Min Act: -0.0000

Data Index: 971351 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1039010 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5432. Min Act: -0.0000

Data Index: 20428 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1187761 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5210. Min Act: -0.0000

Data Index: 186400 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1295373 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5180. Min Act: -0.0000

Data Index: 709486 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.5082. Min Act: -0.0000

Data Index: 458686 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1296490 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4189. Min Act: -0.0000

Data Index: 971571 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4742. Min Act: -0.0000

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4855. Min Act: -0.0000

Data Index: 549678 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4989. Min Act: -0.0000

Data Index: 481282 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4518. Min Act: -0.0000

Data Index: 171065 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.5718. Min Range: -1.5718

Max Act: 0.4946. Min Act: -0.0000

Data Index: 564813 (C4 (Web Text))

Max Activating Token Index: 218