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

Dataset: The Pile

Neuron 4075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.8461. Min Act: -0.0000

Data Index: 804361 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1726809 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1204422 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3429. Min Act: -0.0000

Data Index: 769455 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1501051 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2884. Min Act: -0.0000

Data Index: 91688 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1162285 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2668. Min Act: -0.0000

Data Index: 675721 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3321. Min Act: -0.0000

Data Index: 534898 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.5396. Min Act: -0.0000

Data Index: 1868169 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1439472 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1284688 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2106. Min Act: -0.0000

Data Index: 36160 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2750. Min Act: -0.0000

Data Index: 710902 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3339. Min Act: -0.0000

Data Index: 485219 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.3448. Min Act: -0.0000

Data Index: 850139 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1861840 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 1.8461. Min Range: -1.8461

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1611432 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.4565. Min Act: -0.0000

Data Index: 923963 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 1.8461. Min Range: -1.8461

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1031977 (The Pile)

Max Activating Token Index: 999