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

Dataset: The Pile

Neuron 302 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: 1.1987. Min Range: -1.1987

Max Act: 1.1987. Min Act: -0.0000

Data Index: 1384898 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1389167 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0779. Min Act: -0.0000

Data Index: 946439 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0598. Min Act: -0.0000

Data Index: 415852 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0523. Min Act: -0.0000

Data Index: 918554 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1004384 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0636. Min Act: -0.0000

Data Index: 974256 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9247. Min Act: -0.0000

Data Index: 595366 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1561141 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9096. Min Act: -0.0000

Data Index: 290819 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9675. Min Act: -0.0000

Data Index: 424802 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1297312 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9786. Min Act: -0.0000

Data Index: 911349 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8623. Min Act: -0.0000

Data Index: 631765 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8788. Min Act: -0.0000

Data Index: 88224 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8808. Min Act: -0.0000

Data Index: 414299 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8505. Min Act: -0.0000

Data Index: 689009 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8514. Min Act: -0.0000

Data Index: 720119 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8160. Min Act: -0.0000

Data Index: 750489 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8160. Min Act: -0.0000

Data Index: 156307 (The Pile)

Max Activating Token Index: 111