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

Dataset: The Pile

Neuron 1366 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: 0.3888. Min Range: -0.3888

Max Act: 0.3888. Min Act: -0.0000

Data Index: 134237 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2982. Min Act: -0.0000

Data Index: 931753 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1712256 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1585071 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2683. Min Act: -0.0000

Data Index: 400388 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1562767 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2481. Min Act: -0.0000

Data Index: 114024 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2258. Min Act: -0.0000

Data Index: 621338 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1445158 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1055472 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1003720 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1599235 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1446669 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2263. Min Act: -0.0000

Data Index: 11086 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2145. Min Act: -0.0000

Data Index: 417412 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.1988. Min Act: -0.0000

Data Index: 363314 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1618928 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1114946 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1375946 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1652246 (The Pile)

Max Activating Token Index: 378