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

Dataset: The Pile

Neuron 2196 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1144051 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.5731. Min Act: -0.0000

Data Index: 763979 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1772822 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1042806 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1469569 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.2501. Min Act: 0.0000

Data Index: 814643 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.3232. Min Act: 0.0000

Data Index: 1291183 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.2129. Min Act: -0.0000

Data Index: 35428 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1619735 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.3523. Min Act: 0.0000

Data Index: 1982757 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1273995 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.1928. Min Act: -0.0000

Data Index: 870086 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1195593 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.1568. Min Act: 0.0000

Data Index: 1075443 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.2324. Min Act: 0.0000

Data Index: 1422800 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1800493 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 1.6512. Min Range: -1.6512

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1026621 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0886. Min Act: -0.0000

Data Index: 723250 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1136794 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.6512. Min Range: -1.6512

Max Act: 1.0939. Min Act: -0.0000

Data Index: 912695 (The Pile)

Max Activating Token Index: 655