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

Dataset: The Pile

Neuron 3229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4191. Min Act: -0.0000

Data Index: 946000 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4196. Min Act: -0.0000

Data Index: 728882 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1915946 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1458112 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1108286 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1296076 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4354. Min Act: -0.0001

Data Index: 175154 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4398. Min Act: -0.0000

Data Index: 174364 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1170246 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1638247 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3477. Min Act: -0.0000

Data Index: 905468 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3934. Min Act: -0.0000

Data Index: 50526 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3287. Min Act: -0.0000

Data Index: 577828 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3226. Min Act: -0.0000

Data Index: 762955 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1521664 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.2798. Min Act: -0.0000

Data Index: 44372 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1269701 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1932478 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1094443 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1086138 (The Pile)

Max Activating Token Index: 746