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

Dataset: The Pile

Neuron 2934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1785628 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.4363. Min Act: -0.0000

Data Index: 448933 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.3758. Min Act: -0.0000

Data Index: 986766 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2678. Min Act: -0.0000

Data Index: 801587 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1460659 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1281570 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2987. Min Act: -0.0000

Data Index: 528345 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1898823 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1743234 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1448969 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1511. Min Act: -0.0000

Data Index: 798834 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1898055 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1524812 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1071082 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1475. Min Act: -0.0000

Data Index: 955709 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.0986. Min Act: -0.0000

Data Index: 546378 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1067. Min Act: -0.0000

Data Index: 746777 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1513170 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1176454 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 1.5786. Min Range: -1.5786

Max Act: 1.1357. Min Act: -0.0000

Data Index: 713793 (The Pile)

Max Activating Token Index: 32