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

Dataset: The Pile

Neuron 3827 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: 1.1049. Min Range: -1.1049

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1694258 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1213894 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7886. Min Act: -0.0000

Data Index: 866480 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1793166 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1856401 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7165. Min Act: -0.0000

Data Index: 642507 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.7800. Min Act: -0.0000

Data Index: 932132 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1083709 (The Pile)

Max Activating Token Index: 92

Text #8

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.6904. Min Act: -0.0000

Data Index: 792537 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1276113 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1097953 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5666. Min Act: -0.0000

Data Index: 363685 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5826. Min Act: -0.0000

Data Index: 376757 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1975981 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.6056. Min Act: -0.0000

Data Index: 998642 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5942. Min Act: -0.0000

Data Index: 873046 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1242241 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5580. Min Act: -0.0000

Data Index: 729984 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1005291 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.1049. Min Range: -1.1049

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1108768 (The Pile)

Max Activating Token Index: 576