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

Dataset: The Pile

Neuron 1755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.5995. Min Act: 0.0000

Data Index: 102651 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.5046. Min Act: -0.0000

Data Index: 568994 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3878. Min Act: -0.0000

Data Index: 895914 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2921. Min Act: -0.0000

Data Index: 982833 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1840707 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3293. Min Act: -0.0000

Data Index: 389839 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3299. Min Act: 0.0000

Data Index: 1433509 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3225. Min Act: -0.0000

Data Index: 998446 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1027097 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1686027 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1032969 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1635591 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2795. Min Act: -0.0000

Data Index: 902163 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2750. Min Act: -0.0000

Data Index: 75409 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2630. Min Act: -0.0000

Data Index: 653425 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2764. Min Act: -0.0000

Data Index: 952287 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1640169 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.1679. Min Act: 0.0000

Data Index: 672641 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1539585 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1670164 (The Pile)

Max Activating Token Index: 370