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

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

Neuron 3568 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: 6.8393. Min Range: -6.8393

Max Act: 6.6289. Min Act: -0.0001

Data Index: 241624 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.6782. Min Act: -0.0001

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.7555. Min Act: -0.0000

Data Index: 111451 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.8393. Min Act: -0.0000

Data Index: 1060858 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.2001. Min Act: -0.0000

Data Index: 1352236 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.4512. Min Act: -0.0000

Data Index: 1097383 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.4481. Min Act: -0.0000

Data Index: 184989 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.3942. Min Act: -0.0000

Data Index: 693624 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 6.8393. Min Range: -6.8393

Max Act: 5.6748. Min Act: -0.0000

Data Index: 544794 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 6.8393. Min Range: -6.8393

Max Act: 5.6710. Min Act: -0.0000

Data Index: 142534 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 6.8393. Min Range: -6.8393

Max Act: 5.7496. Min Act: -0.0001

Data Index: 750563 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.2474. Min Act: -0.0000

Data Index: 145494 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.0959. Min Act: -0.0001

Data Index: 1097500 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 6.8393. Min Range: -6.8393

Max Act: 5.9076. Min Act: -0.0000

Data Index: 386585 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.0413. Min Act: -0.0000

Data Index: 317220 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.5934. Min Act: -0.0000

Data Index: 1340435 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.3740. Min Act: -0.0000

Data Index: 1091226 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.0260. Min Act: -0.0000

Data Index: 1183466 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 6.8393. Min Range: -6.8393

Max Act: 5.9849. Min Act: -0.0000

Data Index: 896710 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 6.8393. Min Range: -6.8393

Max Act: 6.1065. Min Act: -0.0001

Data Index: 61677 (C4 (Web Text))

Max Activating Token Index: 821