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

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

Neuron 5413 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: 2.7376. Min Range: -2.7376

Max Act: 2.5161. Min Act: -0.0000

Data Index: 410561 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.3607. Min Act: -0.0000

Data Index: 217298 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.7376. Min Act: -0.0000

Data Index: 1163645 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.6232. Min Act: -0.0000

Data Index: 12452 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.1821. Min Act: -0.0000

Data Index: 1204267 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.4200. Min Act: -0.0000

Data Index: 965239 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.4117. Min Act: -0.0000

Data Index: 268663 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.4725. Min Act: -0.0000

Data Index: 599802 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.2219. Min Act: -0.0000

Data Index: 915149 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.3309. Min Act: -0.0000

Data Index: 285857 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.2276. Min Act: -0.0000

Data Index: 190066 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.4271. Min Act: -0.0001

Data Index: 340396 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.3198. Min Act: -0.0000

Data Index: 1009347 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 2.7376. Min Range: -2.7376

Max Act: 1.9721. Min Act: -0.0000

Data Index: 662830 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.0323. Min Act: -0.0000

Data Index: 5597 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.2467. Min Act: -0.0000

Data Index: 311087 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 2.7376. Min Range: -2.7376

Max Act: 1.9958. Min Act: -0.0000

Data Index: 774242 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.0632. Min Act: -0.0000

Data Index: 285743 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.0358. Min Act: -0.0000

Data Index: 1023919 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.7376. Min Range: -2.7376

Max Act: 2.1482. Min Act: -0.0001

Data Index: 888665 (C4 (Web Text))

Max Activating Token Index: 710