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

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

Neuron 513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3712. Min Act: -0.0000

Data Index: 47376 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3571. Min Act: -0.0000

Data Index: 2818 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3442. Min Act: -0.0000

Data Index: 822558 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3340. Min Act: -0.0000

Data Index: 208608 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3240. Min Act: -0.0000

Data Index: 623085 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1346451 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3336. Min Act: -0.0000

Data Index: 869796 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1238284 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3167. Min Act: -0.0000

Data Index: 360485 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3258. Min Act: -0.0000

Data Index: 790180 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1102206 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3028. Min Act: -0.0000

Data Index: 779846 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2995. Min Act: -0.0000

Data Index: 372809 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2944. Min Act: -0.0000

Data Index: 585202 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1279584 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1349118 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2939. Min Act: -0.0000

Data Index: 381498 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2900. Min Act: -0.0000

Data Index: 552645 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1116614 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.3712. Min Range: -0.3712

Max Act: 0.2893. Min Act: -0.0000

Data Index: 339820 (C4 (Web Text))

Max Activating Token Index: 476