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

Dataset: The Pile

Neuron 2252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1495984 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4485. Min Act: -0.0000

Data Index: 424511 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1342536 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4138. Min Act: -0.0000

Data Index: 495359 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4035. Min Act: -0.0000

Data Index: 482969 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1940368 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1156416 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3680. Min Act: -0.0000

Data Index: 197709 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3657. Min Act: -0.0000

Data Index: 215994 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1836898 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1912193 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1677029 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1030402 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1268363 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3625. Min Act: -0.0000

Data Index: 711319 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3510. Min Act: -0.0000

Data Index: 561749 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1701661 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1715410 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1452248 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3263. Min Act: -0.0000

Data Index: 111489 (The Pile)

Max Activating Token Index: 1019