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

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

Neuron 4027 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8592. Min Act: -0.0000

Data Index: 105573 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7822. Min Act: -0.0000

Data Index: 61738 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7129. Min Act: -0.0000

Data Index: 617635 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7409. Min Act: -0.0000

Data Index: 351575 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7233. Min Act: -0.0000

Data Index: 929839 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7472. Min Act: -0.0000

Data Index: 303366 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7450. Min Act: -0.0000

Data Index: 885839 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7063. Min Act: 0.0000

Data Index: 549870 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7128. Min Act: 0.0000

Data Index: 879582 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6756. Min Act: -0.0000

Data Index: 24081 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8008. Min Act: -0.0000

Data Index: 279037 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1105295 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6881. Min Act: -0.0000

Data Index: 197203 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6632. Min Act: -0.0000

Data Index: 358521 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6355. Min Act: -0.0000

Data Index: 764943 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6975. Min Act: 0.0000

Data Index: 1142644 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6366. Min Act: -0.0000

Data Index: 765078 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6541. Min Act: -0.0000

Data Index: 30265 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6653. Min Act: -0.0000

Data Index: 930834 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6638. Min Act: -0.0000

Data Index: 275109 (C4 (Web Text))

Max Activating Token Index: 92