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

Dataset: The Pile

Neuron 92 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: 1.0181. Min Range: -1.0181

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1527638 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1541583 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7605. Min Act: -0.0000

Data Index: 515467 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7766. Min Act: -0.0000

Data Index: 865796 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7234. Min Act: -0.0000

Data Index: 456504 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1226244 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7294. Min Act: -0.0000

Data Index: 144969 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1292172 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1650348 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1023952 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5439. Min Act: -0.0000

Data Index: 818096 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5493. Min Act: -0.0000

Data Index: 752785 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1724568 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1131550 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1022711 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1919360 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.4956. Min Act: -0.0000

Data Index: 604853 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1776257 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1376783 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.4603. Min Act: -0.0000

Data Index: 964537 (The Pile)

Max Activating Token Index: 164