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

Dataset: The Pile

Neuron 1070 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: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 321921 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1798855 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1872643 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1643402 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1978419 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5720. Min Act: -0.0000

Data Index: 824789 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1275600 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1303470 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1588496 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1488261 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1554087 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1207570 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1594038 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1671607 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1986442 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5922. Min Act: -0.0000

Data Index: 243172 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5829. Min Act: -0.0000

Data Index: 276162 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1496862 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1176429 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1288000 (The Pile)

Max Activating Token Index: 484