Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1692. Min Act: -0.0000

Data Index: 961922 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8583. Min Act: -0.0000

Data Index: 608911 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8468. Min Act: -0.0000

Data Index: 275321 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1570493 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7761. Min Act: -0.0000

Data Index: 82489 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1336916 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7471. Min Act: -0.0000

Data Index: 532586 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7636. Min Act: -0.0000

Data Index: 46531 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1934116 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1766200 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7309. Min Act: -0.0000

Data Index: 295860 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7715. Min Act: -0.0000

Data Index: 747790 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1000691 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1653088 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1887276 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1242869 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1946457 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7230. Min Act: -0.0000

Data Index: 145940 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7568. Min Act: -0.0000

Data Index: 535652 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7257. Min Act: -0.0000

Data Index: 704565 (The Pile)

Max Activating Token Index: 732