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

Dataset: The Pile

Neuron 1092 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: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0000

Data Index: 95852 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4349. Min Act: -0.0000

Data Index: 420749 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1571460 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3799. Min Act: -0.0000

Data Index: 736491 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3488. Min Act: -0.0000

Data Index: 91228 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4044. Min Act: -0.0000

Data Index: 880906 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3776. Min Act: -0.0000

Data Index: 359005 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1267225 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3628. Min Act: -0.0000

Data Index: 645030 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3325. Min Act: -0.0000

Data Index: 387750 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1083060 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3618. Min Act: -0.0000

Data Index: 383159 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3476. Min Act: -0.0000

Data Index: 557808 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3591. Min Act: -0.0000

Data Index: 257574 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1017222 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1312431 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1159 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1085691 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1113753 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1889519 (The Pile)

Max Activating Token Index: 640