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

Dataset: The Pile

Neuron 4437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1586708 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1032363 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3259. Min Act: -0.0000

Data Index: 278662 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2793. Min Act: -0.0000

Data Index: 75974 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3001. Min Act: -0.0000

Data Index: 724442 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3017. Min Act: -0.0000

Data Index: 915621 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2814. Min Act: -0.0000

Data Index: 185979 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1840843 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2637. Min Act: -0.0000

Data Index: 710975 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2662. Min Act: -0.0000

Data Index: 577671 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1879537 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1202300 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2560. Min Act: -0.0000

Data Index: 106633 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1757763 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1535281 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2433. Min Act: -0.0000

Data Index: 904162 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2411. Min Act: -0.0000

Data Index: 588325 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1139275 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1697528 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2247. Min Act: -0.0000

Data Index: 540555 (The Pile)

Max Activating Token Index: 914