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

Dataset: The Pile

Neuron 551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1916811 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5750. Min Act: 0.0000

Data Index: 576227 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1661464 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1325578 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5476. Min Act: -0.0000

Data Index: 312526 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1781343 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4685. Min Act: -0.0000

Data Index: 398524 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5384. Min Act: -0.0000

Data Index: 835894 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1770150 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1336169 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5310. Min Act: -0.0000

Data Index: 903399 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1482378 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1086306 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5183. Min Act: -0.0000

Data Index: 841156 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1383133 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1444614 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5058. Min Act: -0.0000

Data Index: 436077 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1379138 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1365788 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5152. Min Act: -0.0000

Data Index: 46732 (The Pile)

Max Activating Token Index: 981