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

Dataset: The Pile

Neuron 3121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.5175. Min Act: -0.0000

Data Index: 284759 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4789. Min Act: -0.0000

Data Index: 620101 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4619. Min Act: -0.0000

Data Index: 86925 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4555. Min Act: -0.0000

Data Index: 459179 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1912592 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4485. Min Act: -0.0000

Data Index: 772057 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4330. Min Act: -0.0000

Data Index: 972285 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1723724 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4032. Min Act: -0.0000

Data Index: 830765 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3935. Min Act: -0.0000

Data Index: 172156 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4170. Min Act: -0.0000

Data Index: 653837 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1927161 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1257489 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3977. Min Act: -0.0000

Data Index: 897405 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1591648 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3988. Min Act: -0.0000

Data Index: 985112 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1645131 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3980. Min Act: -0.0000

Data Index: 976329 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1705896 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1269883 (The Pile)

Max Activating Token Index: 742