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

Dataset: The Pile

Neuron 868 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: 0.6158. Min Act: -0.0000

Data Index: 635838 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1290193 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.2128. Min Act: -0.0000

Data Index: 508715 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1640. Min Act: -0.0000

Data Index: 783548 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1322605 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1851. Min Act: -0.0000

Data Index: 163302 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1879560 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1496. Min Act: -0.0000

Data Index: 560861 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1445. Min Act: -0.0000

Data Index: 262398 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1592. Min Act: -0.0000

Data Index: 935508 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1148360 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1809609 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1973319 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1448. Min Act: -0.0000

Data Index: 364862 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1254. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1953791 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1355036 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1402. Min Act: -0.0000

Data Index: 341927 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1544535 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 1008