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

Dataset: The Pile

Neuron 206 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: 1.1059. Min Range: -1.1059

Max Act: 1.0388. Min Act: -0.0000

Data Index: 895440 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.1059. Min Range: -1.1059

Max Act: 1.1059. Min Act: -0.0000

Data Index: 41941 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1428313 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8041. Min Act: -0.0000

Data Index: 158514 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1023983 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7118. Min Act: -0.0000

Data Index: 365249 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1744591 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7658. Min Act: -0.0000

Data Index: 133799 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1881323 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1978215 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1871323 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1253085 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7577. Min Act: -0.0000

Data Index: 878821 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7389. Min Act: -0.0000

Data Index: 383492 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1709255 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7600. Min Act: -0.0000

Data Index: 47534 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7158. Min Act: -0.0000

Data Index: 369323 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1998293 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1284014 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 1.1059. Min Range: -1.1059

Max Act: 0.6964. Min Act: -0.0000

Data Index: 81712 (The Pile)

Max Activating Token Index: 190