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

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

Neuron 24 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.5917. Min Act: -0.0000

Data Index: 195731 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.3743. Min Act: -0.0000

Data Index: 122095 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.2857. Min Act: -0.0000

Data Index: 389337 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.3954. Min Act: -0.0000

Data Index: 917547 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.4485. Min Act: -0.0000

Data Index: 592718 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1351367 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.3116. Min Act: -0.0001

Data Index: 948226 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.2866. Min Act: -0.0001

Data Index: 752995 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.2412. Min Act: -0.0000

Data Index: 881980 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.2702. Min Act: -0.0000

Data Index: 990708 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.2503. Min Act: -0.0000

Data Index: 329424 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.0200. Min Act: -0.0000

Data Index: 504390 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.1871. Min Act: -0.0000

Data Index: 510891 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.1770. Min Act: -0.0000

Data Index: 1039190 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1118457 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1196741 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.1336. Min Act: -0.0000

Data Index: 774136 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.1315. Min Act: -0.0000

Data Index: 945601 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.5917. Min Range: -2.5917

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1290849 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 2.5917. Min Range: -2.5917

Max Act: 1.9872. Min Act: -0.0000

Data Index: 792387 (C4 (Web Text))

Max Activating Token Index: 609