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

Dataset: The Pile

Neuron 3853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3432. Min Act: 0.0000

Data Index: 1736342 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1771684 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3342. Min Act: -0.0000

Data Index: 693479 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1925163 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3325. Min Act: -0.0000

Data Index: 973637 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1723636 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1643771 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3275. Min Act: -0.0000

Data Index: 107973 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1790968 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3352. Min Act: -0.0000

Data Index: 267657 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1888058 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3119. Min Act: -0.0000

Data Index: 923891 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3131. Min Act: -0.0000

Data Index: 204525 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3015. Min Act: -0.0000

Data Index: 39806 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1854307 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3111. Min Act: -0.0000

Data Index: 679808 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2981. Min Act: -0.0000

Data Index: 356335 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2837. Min Act: -0.0000

Data Index: 781549 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1243357 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.3595. Min Range: -0.3595

Max Act: 0.2815. Min Act: -0.0000

Data Index: 19950 (The Pile)

Max Activating Token Index: 463