Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6280. Min Act: -0.0000

Data Index: 790965 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1824886 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5196. Min Act: -0.0000

Data Index: 599276 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1580155 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3415. Min Act: -0.0000

Data Index: 242089 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5202. Min Act: -0.0000

Data Index: 520486 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1461835 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4280. Min Act: -0.0000

Data Index: 650593 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3388. Min Act: -0.0000

Data Index: 296146 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2935. Min Act: -0.0000

Data Index: 451964 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1866817 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2504. Min Act: -0.0000

Data Index: 380798 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1929022 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3009. Min Act: -0.0000

Data Index: 48626 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2427. Min Act: -0.0000

Data Index: 738529 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3250. Min Act: -0.0000

Data Index: 467517 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1374894 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1475062 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1626126 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.1781. Min Act: -0.0000

Data Index: 873836 (The Pile)

Max Activating Token Index: 235