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

Dataset: The Pile

Neuron 3086 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1903772 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1852103 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4532. Min Act: -0.0000

Data Index: 242636 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1261003 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4039. Min Act: -0.0000

Data Index: 982447 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1813514 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3508. Min Act: -0.0000

Data Index: 127672 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1761473 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1557530 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1219160 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1582355 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3358. Min Act: -0.0000

Data Index: 368149 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1336497 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1420080 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3316. Min Act: -0.0000

Data Index: 724153 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3169. Min Act: -0.0000

Data Index: 141296 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3048. Min Act: -0.0000

Data Index: 968280 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1298971 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1857787 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1186590 (The Pile)

Max Activating Token Index: 807