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

Dataset: The Pile

Neuron 2699 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: 0.8189. Min Range: -0.8189

Max Act: 0.8189. Min Act: -0.0000

Data Index: 978679 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1587424 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1425016 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7063. Min Act: -0.0000

Data Index: 911690 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6854. Min Act: -0.0000

Data Index: 693153 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1101628 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6625. Min Act: -0.0000

Data Index: 818795 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6136. Min Act: -0.0000

Data Index: 626296 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6589. Min Act: -0.0000

Data Index: 829200 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1665190 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1160651 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6595. Min Act: -0.0000

Data Index: 524446 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1105449 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6777. Min Act: -0.0000

Data Index: 75807 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1313991 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6037. Min Act: -0.0000

Data Index: 524680 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1508464 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1036123 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6177. Min Act: -0.0000

Data Index: 338861 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6000. Min Act: -0.0000

Data Index: 973911 (The Pile)

Max Activating Token Index: 378