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

Dataset: The Pile

Neuron 1080 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: 0.9883. Min Range: -0.9883

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1096571 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8456. Min Act: -0.0000

Data Index: 368325 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7752. Min Act: -0.0000

Data Index: 23729 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6955. Min Act: -0.0000

Data Index: 865676 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6617. Min Act: -0.0000

Data Index: 477383 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1581979 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6479. Min Act: -0.0000

Data Index: 340784 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6331. Min Act: -0.0000

Data Index: 682147 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1730751 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6325. Min Act: -0.0000

Data Index: 361937 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6835. Min Act: -0.0000

Data Index: 700467 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.5990. Min Act: -0.0000

Data Index: 906421 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.5694. Min Act: -0.0000

Data Index: 850325 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1069103 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1324750 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6635. Min Act: -0.0000

Data Index: 911128 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1306470 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1047641 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6218. Min Act: -0.0000

Data Index: 592915 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.5980. Min Act: -0.0000

Data Index: 866484 (The Pile)

Max Activating Token Index: 266