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

Dataset: The Pile

Neuron 3633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1014346 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8893. Min Act: -0.0000

Data Index: 351967 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8358. Min Act: -0.0000

Data Index: 14788 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8331. Min Act: -0.0000

Data Index: 307773 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8083. Min Act: -0.0000

Data Index: 340584 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7856. Min Act: -0.0000

Data Index: 900094 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7821. Min Act: -0.0000

Data Index: 563633 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6719. Min Act: -0.0000

Data Index: 950914 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1529916 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1110715 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6692. Min Act: -0.0000

Data Index: 235369 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7204. Min Act: -0.0000

Data Index: 299630 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6552. Min Act: -0.0000

Data Index: 757296 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1019272 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1286926 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1565276 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7103. Min Act: -0.0000

Data Index: 419751 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7102. Min Act: -0.0000

Data Index: 993248 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.6796. Min Act: -0.0000

Data Index: 68890 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1181317 (The Pile)

Max Activating Token Index: 103