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

Dataset: The Pile

Neuron 3574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1336895 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0165. Min Act: -0.0000

Data Index: 508456 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0354. Min Act: -0.0000

Data Index: 793820 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1806928 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1782308 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1357033 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9064. Min Act: -0.0000

Data Index: 880121 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8086. Min Act: -0.0000

Data Index: 950250 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1250185 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8580. Min Act: -0.0000

Data Index: 921906 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8474. Min Act: -0.0000

Data Index: 12759 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1493358 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8179. Min Act: -0.0000

Data Index: 725956 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1180641 (The Pile)

Max Activating Token Index: 868

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7664. Min Act: -0.0000

Data Index: 850272 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7784. Min Act: -0.0000

Data Index: 611830 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.6984. Min Act: -0.0000

Data Index: 319509 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1818302 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7713. Min Act: -0.0000

Data Index: 410654 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1388707 (The Pile)

Max Activating Token Index: 953