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

Dataset: The Pile

Neuron 525 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: 1.5208. Min Range: -1.5208

Max Act: 1.5208. Min Act: -0.0000

Data Index: 163775 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3111. Min Act: -0.0000

Data Index: 75513 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2306. Min Act: -0.0000

Data Index: 921674 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1925245 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1448055 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0809. Min Act: -0.0000

Data Index: 420636 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0321. Min Act: -0.0000

Data Index: 830414 (The Pile)

Max Activating Token Index: 595

Text #7

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1753254 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1251832 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0804. Min Act: -0.0000

Data Index: 450648 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1100209 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0478. Min Act: -0.0000

Data Index: 412340 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1022432 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1898519 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.9964. Min Act: -0.0000

Data Index: 844968 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.9971. Min Act: -0.0000

Data Index: 589393 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1706434 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.8800. Min Act: -0.0000

Data Index: 759920 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0020. Min Act: -0.0000

Data Index: 123532 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.5208. Min Range: -1.5208

Max Act: 0.8596. Min Act: -0.0000

Data Index: 86918 (The Pile)

Max Activating Token Index: 880