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

Dataset: The Pile

Neuron 2146 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: 0.7855. Min Range: -0.7855

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1338264 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1093253 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6620. Min Act: -0.0000

Data Index: 136077 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6488. Min Act: -0.0000

Data Index: 55238 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7855. Min Act: -0.0000

Data Index: 228332 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6059. Min Act: -0.0000

Data Index: 179306 (The Pile)

Max Activating Token Index: 581

Text #6

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6114. Min Act: -0.0000

Data Index: 84413 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6077. Min Act: -0.0000

Data Index: 991688 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1531527 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6138. Min Act: -0.0000

Data Index: 279749 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6251. Min Act: -0.0000

Data Index: 264474 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1410688 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1093089 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1215455 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6193. Min Act: -0.0000

Data Index: 46204 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1729369 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6014. Min Act: -0.0000

Data Index: 611516 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6043. Min Act: -0.0000

Data Index: 59600 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6182. Min Act: -0.0000

Data Index: 313399 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1120256 (The Pile)

Max Activating Token Index: 274