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

Dataset: The Pile

Neuron 3801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.7777. Min Act: -0.0000

Data Index: 506888 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 1.0626. Min Range: -1.0626

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1667798 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.0626. Min Range: -1.0626

Max Act: 1.0329. Min Act: -0.0000

Data Index: 389 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.0626. Min Range: -1.0626

Max Act: 1.0125. Min Act: -0.0000

Data Index: 435940 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1315467 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1706159 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1954075 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1161132 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1802596 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9125. Min Act: -0.0000

Data Index: 861145 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9355. Min Act: -0.0000

Data Index: 443231 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1637315 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9272. Min Act: -0.0000

Data Index: 148187 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1413124 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1811846 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1758916 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1416261 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1747059 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8606. Min Act: -0.0000

Data Index: 787365 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8361. Min Act: -0.0000

Data Index: 117321 (The Pile)

Max Activating Token Index: 216