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

Dataset: The Pile

Neuron 2000 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: 1.5453. Min Range: -1.5453

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1424362 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.5390. Min Act: -0.0000

Data Index: 736231 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4744. Min Act: -0.0000

Data Index: 690716 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3340. Min Act: -0.0000

Data Index: 1377512 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1004766 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2493. Min Act: -0.0000

Data Index: 463577 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1402. Min Act: -0.0000

Data Index: 220264 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1330727 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1808500 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1211. Min Act: -0.0000

Data Index: 648083 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1068821 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1812196 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0271. Min Act: -0.0000

Data Index: 486095 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1867812 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1028739 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9253. Min Act: -0.0000

Data Index: 363808 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1420523 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0200. Min Act: -0.0000

Data Index: 206720 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1924456 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9078. Min Act: -0.0000

Data Index: 584688 (The Pile)

Max Activating Token Index: 300