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

Dataset: The Pile

Neuron 1696 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: 0.3826. Min Range: -0.3826

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1407922 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1000909 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3415. Min Act: -0.0000

Data Index: 496105 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3415. Min Act: -0.0000

Data Index: 706850 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1177185 (The Pile)

Max Activating Token Index: 891

Text #5

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1601248 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1684631 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1057248 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1368867 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3174. Min Act: -0.0000

Data Index: 323874 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1795532 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3218. Min Act: -0.0000

Data Index: 15372 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3105. Min Act: -0.0000

Data Index: 830154 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1779812 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3355. Min Act: -0.0000

Data Index: 770454 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1546277 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1237824 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3025. Min Act: -0.0000

Data Index: 625573 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1998535 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1370286 (The Pile)

Max Activating Token Index: 806