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

Dataset: The Pile

Neuron 2433 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: 1.7962. Min Range: -1.7962

Max Act: 1.7663. Min Act: -0.0000

Data Index: 737981 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.7962. Min Act: -0.0000

Data Index: 1943077 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.6515. Min Act: -0.0000

Data Index: 654025 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.3946. Min Act: -0.0000

Data Index: 831240 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.2556. Min Act: -0.0000

Data Index: 150478 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1052127 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.2484. Min Act: -0.0000

Data Index: 637177 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1916. Min Act: -0.0000

Data Index: 445497 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.2110. Min Act: -0.0000

Data Index: 897274 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1970. Min Act: -0.0000

Data Index: 490321 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1347489 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1217365 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1792. Min Act: -0.0000

Data Index: 297134 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1100357 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1513. Min Act: -0.0000

Data Index: 45190 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.0368. Min Act: -0.0000

Data Index: 865054 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1126587 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.0444. Min Act: -0.0000

Data Index: 663526 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.1448. Min Act: -0.0000

Data Index: 826796 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.7962. Min Range: -1.7962

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1829702 (The Pile)

Max Activating Token Index: 1019