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

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

Neuron 1950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.5358. Min Act: -0.0002

Data Index: 794370 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.3071. Min Act: -0.0002

Data Index: 177398 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.2399. Min Act: -0.0002

Data Index: 817409 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.1792. Min Act: -0.0002

Data Index: 260092 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.1917. Min Act: -0.0002

Data Index: 807001 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0936. Min Act: -0.0002

Data Index: 466029 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.1328. Min Act: -0.0002

Data Index: 925421 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.1303. Min Act: -0.0002

Data Index: 600087 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0903. Min Act: -0.0002

Data Index: 764985 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0770. Min Act: -0.0002

Data Index: 1229287 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0459. Min Act: -0.0002

Data Index: 202231 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0995. Min Act: -0.0002

Data Index: 1088160 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0418. Min Act: -0.0002

Data Index: 183571 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0175. Min Act: -0.0002

Data Index: 1349093 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0150. Min Act: -0.0002

Data Index: 938401 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.5358. Min Range: -1.5358

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1050138 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.5358. Min Range: -1.5358

Max Act: 0.9618. Min Act: -0.0002

Data Index: 126961 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.5358. Min Range: -1.5358

Max Act: 0.9841. Min Act: -0.0002

Data Index: 125402 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.5358. Min Range: -1.5358

Max Act: 0.9856. Min Act: -0.0002

Data Index: 1237131 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.5358. Min Range: -1.5358

Max Act: 0.9812. Min Act: -0.0002

Data Index: 676939 (C4 (Web Text))

Max Activating Token Index: 637