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

Dataset: The Pile

Neuron 1663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4419. Min Act: -0.0000

Data Index: 792219 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1185127 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3760. Min Act: -0.0000

Data Index: 193993 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3784. Min Act: -0.0000

Data Index: 635507 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1254273 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1048149 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3558. Min Act: -0.0000

Data Index: 457721 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3367. Min Act: -0.0000

Data Index: 785564 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1069219 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3406. Min Act: -0.0000

Data Index: 618930 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1628069 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1278577 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1057848 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2809. Min Act: -0.0000

Data Index: 340294 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1141449 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1383389 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2614. Min Act: -0.0000

Data Index: 60521 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2762. Min Act: -0.0000

Data Index: 125309 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1969740 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1138664 (The Pile)

Max Activating Token Index: 1006