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

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

Neuron 2737 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0967. Min Range: -4.0967

Max Act: 4.0967. Min Act: -0.0000

Data Index: 511035 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.8996. Min Act: -0.0000

Data Index: 148346 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.8227. Min Act: -0.0000

Data Index: 514642 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.5442. Min Act: -0.0000

Data Index: 254694 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.4893. Min Act: -0.0000

Data Index: 477725 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.1667. Min Act: -0.0000

Data Index: 1041271 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.5355. Min Act: -0.0000

Data Index: 75637 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.5003. Min Act: -0.0000

Data Index: 680324 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.4424. Min Act: -0.0000

Data Index: 320477 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.6714. Min Act: -0.0000

Data Index: 342154 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.2714. Min Act: -0.0000

Data Index: 831212 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.2705. Min Act: -0.0000

Data Index: 227942 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.2000. Min Act: -0.0000

Data Index: 122382 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 4.0967. Min Range: -4.0967

Max Act: 2.9714. Min Act: -0.0000

Data Index: 1238269 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.2440. Min Act: -0.0000

Data Index: 345454 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 4.0967. Min Range: -4.0967

Max Act: 2.9550. Min Act: -0.0000

Data Index: 260968 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.2343. Min Act: -0.0000

Data Index: 290656 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.0539. Min Act: -0.0000

Data Index: 971809 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 4.0967. Min Range: -4.0967

Max Act: 2.8517. Min Act: -0.0000

Data Index: 499979 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 4.0967. Min Range: -4.0967

Max Act: 3.1926. Min Act: -0.0000

Data Index: 255630 (C4 (Web Text))

Max Activating Token Index: 817