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

Dataset: The Pile

Neuron 3143 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: 0.4360. Min Range: -0.4360

Max Act: 0.4360. Min Act: -0.0000

Data Index: 278407 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4084. Min Act: -0.0000

Data Index: 932320 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3923. Min Act: -0.0000

Data Index: 802687 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1985202 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3635. Min Act: -0.0000

Data Index: 767257 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3462. Min Act: -0.0000

Data Index: 951356 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3670. Min Act: -0.0000

Data Index: 582289 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1215937 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1798872 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3535. Min Act: -0.0000

Data Index: 272414 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3411. Min Act: -0.0000

Data Index: 981204 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3535. Min Act: -0.0000

Data Index: 94974 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1257341 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3610. Min Act: -0.0000

Data Index: 843643 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3434. Min Act: -0.0000

Data Index: 781723 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1793408 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1508012 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3366. Min Act: -0.0000

Data Index: 349783 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3258. Min Act: -0.0000

Data Index: 211832 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1472699 (The Pile)

Max Activating Token Index: 895