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

Dataset: The Pile

Neuron 4957 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1875223 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.1138. Min Act: -0.0000

Data Index: 664958 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1673211 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1882114 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8326. Min Act: -0.0000

Data Index: 59786 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.0284. Min Act: -0.0000

Data Index: 656782 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.9162. Min Act: -0.0000

Data Index: 928029 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1453759 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8688. Min Act: -0.0000

Data Index: 658766 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1378742 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.6606. Min Act: -0.0000

Data Index: 992618 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8250. Min Act: -0.0000

Data Index: 556810 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.8099. Min Act: -0.0000

Data Index: 145642 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1016419 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1957266 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1629119 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1061099 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7655. Min Act: -0.0000

Data Index: 993061 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7238. Min Act: -0.0000

Data Index: 626692 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7584. Min Act: -0.0000

Data Index: 463972 (The Pile)

Max Activating Token Index: 471