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

Dataset: The Pile

Neuron 3159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1475272 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7764. Min Act: -0.0000

Data Index: 526788 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1770154 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7506. Min Act: -0.0000

Data Index: 351051 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7359. Min Act: -0.0000

Data Index: 806576 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1202944 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7163. Min Act: -0.0000

Data Index: 615119 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6771. Min Act: -0.0000

Data Index: 115885 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1121598 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1935209 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6580. Min Act: -0.0000

Data Index: 332917 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1203216 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1901122 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6458. Min Act: -0.0000

Data Index: 783257 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6252. Min Act: -0.0000

Data Index: 126331 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1029337 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6268. Min Act: -0.0000

Data Index: 68609 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6941. Min Act: -0.0000

Data Index: 462313 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1026888 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1329872 (The Pile)

Max Activating Token Index: 366