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

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

Neuron 3129 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.9301. Min Act: -0.0000

Data Index: 1220057 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.5523. Min Act: -0.0000

Data Index: 913004 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.4850. Min Act: -0.0000

Data Index: 1117707 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.7614. Min Act: -0.0000

Data Index: 1212861 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.4566. Min Act: -0.0000

Data Index: 681880 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.6066. Min Act: -0.0000

Data Index: 215733 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.4087. Min Act: -0.0000

Data Index: 879035 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.4018. Min Act: -0.0000

Data Index: 807991 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2743. Min Act: -0.0000

Data Index: 499285 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2606. Min Act: -0.0000

Data Index: 97373 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2580. Min Act: -0.0000

Data Index: 1158372 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.3716. Min Act: -0.0000

Data Index: 240343 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2090. Min Act: -0.0000

Data Index: 1098821 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.1865. Min Act: -0.0000

Data Index: 246812 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2713. Min Act: -0.0000

Data Index: 1272066 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.2815. Min Act: -0.0000

Data Index: 199862 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 3.9301. Min Range: -3.9301

Max Act: 2.9742. Min Act: -0.0000

Data Index: 824138 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.0636. Min Act: -0.0000

Data Index: 1240628 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.0344. Min Act: -0.0000

Data Index: 776656 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.9301. Min Range: -3.9301

Max Act: 3.0237. Min Act: -0.0000

Data Index: 1128238 (C4 (Web Text))

Max Activating Token Index: 535