Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 514 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 41603 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1248424 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1360260 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0015. Min Act: -0.0000

Data Index: 804856 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1039769 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9509. Min Act: 0.0002

Data Index: 1474488 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1879083 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9598. Min Act: -0.0000

Data Index: 739937 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9217. Min Act: 0.0000

Data Index: 163168 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1743016 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9354. Min Act: -0.0000

Data Index: 991323 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1261746 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1004823 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1438729 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9055. Min Act: 0.0000

Data Index: 755486 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8499. Min Act: -0.0000

Data Index: 370946 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8328. Min Act: -0.0001

Data Index: 469980 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1665586 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8283. Min Act: -0.0000

Data Index: 662410 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8544. Min Act: 0.0000

Data Index: 534618 (The Pile)

Max Activating Token Index: 872