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

Dataset: The Pile

Neuron 2388 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: 1.9955. Min Range: -1.9955

Max Act: 1.9955. Min Act: -0.0000

Data Index: 1145558 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1390606 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8468. Min Act: -0.0000

Data Index: 512354 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8517. Min Act: -0.0000

Data Index: 743915 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8005. Min Act: -0.0000

Data Index: 1236190 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8330. Min Act: -0.0000

Data Index: 336910 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8197. Min Act: -0.0000

Data Index: 1160918 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8140. Min Act: -0.0000

Data Index: 924312 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7733. Min Act: -0.0000

Data Index: 422952 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7721. Min Act: -0.0000

Data Index: 1079916 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7346. Min Act: -0.0000

Data Index: 120680 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7529. Min Act: -0.0000

Data Index: 570138 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6652. Min Act: -0.0000

Data Index: 174566 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7047. Min Act: -0.0000

Data Index: 757537 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6588. Min Act: -0.0000

Data Index: 584540 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6954. Min Act: -0.0000

Data Index: 1396405 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6471. Min Act: -0.0000

Data Index: 580698 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6946. Min Act: -0.0000

Data Index: 1233935 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6826. Min Act: -0.0000

Data Index: 850748 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7250. Min Act: -0.0000

Data Index: 746562 (The Pile)

Max Activating Token Index: 400