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

Dataset: The Pile

Neuron 3296 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: 0.7741. Min Range: -0.7741

Max Act: 0.7276. Min Act: -0.0000

Data Index: 685308 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1646622 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1211297 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1527412 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7040. Min Act: -0.0000

Data Index: 650135 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1953597 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1344685 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1398821 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1935087 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1897491 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1419258 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1912043 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5683. Min Act: -0.0000

Data Index: 110193 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5878. Min Act: -0.0000

Data Index: 646631 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5188. Min Act: -0.0000

Data Index: 671814 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5463. Min Act: -0.0000

Data Index: 384143 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5511. Min Act: -0.0000

Data Index: 702250 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5597. Min Act: -0.0000

Data Index: 777371 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5700. Min Act: -0.0000

Data Index: 58532 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5547. Min Act: -0.0000

Data Index: 511584 (The Pile)

Max Activating Token Index: 989