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

Dataset: The Pile

Neuron 3681 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: 1.1439. Min Range: -1.1439

Max Act: 1.1439. Min Act: -0.0000

Data Index: 63354 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 1.1439. Min Range: -1.1439

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1764920 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.9328. Min Act: -0.0000

Data Index: 988378 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.9323. Min Act: -0.0000

Data Index: 642022 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1889406 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1762436 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8346. Min Act: -0.0000

Data Index: 84811 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8301. Min Act: -0.0000

Data Index: 75350 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8028. Min Act: -0.0000

Data Index: 974652 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1915404 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8325. Min Act: -0.0000

Data Index: 429169 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1900637 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1824237 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7960. Min Act: -0.0000

Data Index: 400677 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7633. Min Act: -0.0000

Data Index: 593990 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.8027. Min Act: -0.0000

Data Index: 689030 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7750. Min Act: -0.0000

Data Index: 782958 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1075167 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7732. Min Act: -0.0000

Data Index: 787356 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.1439. Min Range: -1.1439

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1814935 (The Pile)

Max Activating Token Index: 574