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

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

Neuron 2350 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: 1.0292. Min Range: -1.0292

Max Act: 1.0292. Min Act: -0.0002

Data Index: 771519 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6423. Min Act: -0.0002

Data Index: 783703 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7328. Min Act: -0.0002

Data Index: 635161 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8555. Min Act: -0.0002

Data Index: 26175 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8292. Min Act: -0.0002

Data Index: 354746 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6294. Min Act: -0.0002

Data Index: 220522 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6319. Min Act: -0.0002

Data Index: 665220 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7768. Min Act: -0.0002

Data Index: 659710 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6751. Min Act: -0.0002

Data Index: 324926 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.5916. Min Act: -0.0002

Data Index: 323767 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7965. Min Act: -0.0002

Data Index: 938621 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7818. Min Act: -0.0002

Data Index: 254539 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.5333. Min Act: -0.0002

Data Index: 1387081 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.3964. Min Act: -0.0002

Data Index: 575328 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6235. Min Act: -0.0002

Data Index: 508710 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.5808. Min Act: -0.0002

Data Index: 831107 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.5973. Min Act: -0.0002

Data Index: 1367897 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6967. Min Act: -0.0002

Data Index: 574535 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.6288. Min Act: -0.0002

Data Index: 799769 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.5586. Min Act: -0.0002

Data Index: 597414 (C4 (Web Text))

Max Activating Token Index: 680