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

Dataset: The Pile

Neuron 1945 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.7210. Min Act: -0.0000

Data Index: 9304 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6690. Min Act: -0.0000

Data Index: 201060 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1073460 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5404. Min Act: -0.0000

Data Index: 307288 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5480. Min Act: -0.0000

Data Index: 114778 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5103. Min Act: -0.0000

Data Index: 384195 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5718. Min Act: -0.0000

Data Index: 679949 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5158. Min Act: -0.0000

Data Index: 128843 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5195. Min Act: -0.0000

Data Index: 750383 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1483427 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1225668 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5340. Min Act: -0.0000

Data Index: 770377 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5176. Min Act: -0.0000

Data Index: 776626 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1601358 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1993449 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1077253 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4990. Min Act: -0.0000

Data Index: 373941 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1473197 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4834. Min Act: -0.0000

Data Index: 131217 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1660044 (The Pile)

Max Activating Token Index: 701