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

Dataset: The Pile

Neuron 2276 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: 0.4640. Min Range: -0.4640

Max Act: 0.4640. Min Act: -0.0000

Data Index: 627508 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4202. Min Act: -0.0000

Data Index: 644664 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1178575 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1612299 (The Pile)

Max Activating Token Index: 963

Text #4

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1912193 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3606. Min Act: -0.0000

Data Index: 851048 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3574. Min Act: -0.0000

Data Index: 637600 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3444. Min Act: -0.0000

Data Index: 963413 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3374. Min Act: -0.0000

Data Index: 756458 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1096727 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3352. Min Act: -0.0000

Data Index: 140876 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1216377 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1503301 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1413739 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.2873. Min Act: -0.0000

Data Index: 594297 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1455661 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3246. Min Act: -0.0000

Data Index: 385308 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1117458 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1550174 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1473739 (The Pile)

Max Activating Token Index: 71