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

Dataset: The Pile

Neuron 4200 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: 0.9766. Min Range: -0.9766

Max Act: 0.9766. Min Act: -0.0000

Data Index: 420018 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1714881 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1907718 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1010102 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1215798 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1161202 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6613. Min Act: -0.0000

Data Index: 494631 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6117. Min Act: -0.0000

Data Index: 586863 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1402687 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1671347 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1434893 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1949848 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.5851. Min Act: -0.0000

Data Index: 555878 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.5950. Min Act: -0.0000

Data Index: 123459 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1298541 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1302202 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1182520 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.4722. Min Act: -0.0000

Data Index: 797117 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.6107. Min Act: -0.0000

Data Index: 149356 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.5503. Min Act: -0.0000

Data Index: 492986 (The Pile)

Max Activating Token Index: 153