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

Dataset: The Pile

Neuron 1304 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: 1.9264. Min Range: -1.9264

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1737304 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1731930 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3818. Min Act: -0.0000

Data Index: 813985 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1083859 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3308. Min Act: -0.0000

Data Index: 36599 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3147. Min Act: -0.0000

Data Index: 863407 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1800095 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3073. Min Act: -0.0000

Data Index: 995842 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3283. Min Act: 0.0000

Data Index: 779957 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3308. Min Act: -0.0000

Data Index: 308597 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1360481 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3229. Min Act: -0.0000

Data Index: 575569 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1099499 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1119786 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2994. Min Act: 0.0000

Data Index: 1910151 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2793. Min Act: -0.0000

Data Index: 619608 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2927. Min Act: -0.0000

Data Index: 232765 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1976639 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2671. Min Act: -0.0000

Data Index: 41725 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 1.9264. Min Range: -1.9264

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1800003 (The Pile)

Max Activating Token Index: 538