Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.6364. Min Act: -0.0000

Data Index: 563201 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5821. Min Act: -0.0000

Data Index: 749715 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1079178 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5286. Min Act: -0.0000

Data Index: 859052 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1233540 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5353. Min Act: 0.0001

Data Index: 412038 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.5208. Min Act: -0.0000

Data Index: 66411 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4989. Min Act: -0.0000

Data Index: 582874 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1212084 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4723. Min Act: -0.0000

Data Index: 866264 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4720. Min Act: 0.0000

Data Index: 834585 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4622. Min Act: 0.0002

Data Index: 165790 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1384884 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4580. Min Act: -0.0000

Data Index: 111966 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4514. Min Act: -0.0000

Data Index: 402159 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1195622 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4092. Min Act: 0.0000

Data Index: 939216 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4244. Min Act: -0.0000

Data Index: 348802 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1111925 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.6364. Min Range: -0.6364

Max Act: 0.4200. Min Act: 0.0000

Data Index: 1507240 (Python Code)

Max Activating Token Index: 524