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

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

Neuron 5215 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: 2.5232. Min Range: -2.5232

Max Act: 2.5232. Min Act: -0.0000

Data Index: 1345290 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.2858. Min Act: -0.0000

Data Index: 325612 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.5074. Min Act: -0.0000

Data Index: 1249647 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.2875. Min Act: -0.0000

Data Index: 79599 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.1973. Min Act: -0.0000

Data Index: 548947 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.0414. Min Act: -0.0000

Data Index: 995700 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.0078. Min Act: -0.0000

Data Index: 795248 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.0582. Min Act: -0.0000

Data Index: 252046 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.0462. Min Act: -0.0000

Data Index: 790015 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.1345. Min Act: -0.0000

Data Index: 450968 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 2.5232. Min Range: -2.5232

Max Act: 2.0165. Min Act: -0.0000

Data Index: 885982 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.9250. Min Act: -0.0000

Data Index: 311760 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.8280. Min Act: -0.0000

Data Index: 793946 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.7703. Min Act: -0.0000

Data Index: 798799 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.8342. Min Act: -0.0000

Data Index: 613795 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.8047. Min Act: -0.0000

Data Index: 109177 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.7785. Min Act: -0.0000

Data Index: 177623 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.6695. Min Act: -0.0000

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.7290. Min Act: -0.0000

Data Index: 855133 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 2.5232. Min Range: -2.5232

Max Act: 1.7269. Min Act: -0.0000

Data Index: 321562 (C4 (Web Text))

Max Activating Token Index: 514