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

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

Neuron 1718 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: 3.7386. Min Range: -3.7386

Max Act: 3.6949. Min Act: -0.0000

Data Index: 1278654 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.7043. Min Act: -0.0000

Data Index: 112683 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.6673. Min Act: -0.0000

Data Index: 327720 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.7386. Min Act: -0.0000

Data Index: 372477 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.4913. Min Act: -0.0000

Data Index: 260971 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.5775. Min Act: -0.0000

Data Index: 1320918 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.4075. Min Act: -0.0000

Data Index: 1336725 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.5316. Min Act: -0.0000

Data Index: 459608 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.1850. Min Act: -0.0000

Data Index: 573079 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.3319. Min Act: -0.0000

Data Index: 1223333 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.3228. Min Act: -0.0000

Data Index: 577140 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.3311. Min Act: -0.0000

Data Index: 864654 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.4416. Min Act: -0.0000

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.1279. Min Act: -0.0000

Data Index: 1298115 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2778. Min Act: -0.0000

Data Index: 1336039 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2455. Min Act: -0.0000

Data Index: 584625 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2395. Min Act: -0.0000

Data Index: 526125 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2266. Min Act: -0.0000

Data Index: 45699 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.2105. Min Act: -0.0000

Data Index: 1208629 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 3.7386. Min Range: -3.7386

Max Act: 3.1956. Min Act: -0.0000

Data Index: 2779 (C4 (Web Text))

Max Activating Token Index: 515