Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1736 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2044. Min Act: -0.0000

Data Index: 376965 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1386. Min Act: -0.0000

Data Index: 125120 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2094. Min Act: -0.0000

Data Index: 418720 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2379. Min Act: -0.0000

Data Index: 803287 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1530124 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.1688. Min Act: -0.0000

Data Index: 178112 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1586232 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0230. Min Act: -0.0000

Data Index: 306816 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0115. Min Act: -0.0000

Data Index: 940346 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0379. Min Act: -0.0000

Data Index: 925323 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1219936 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1488406 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9581. Min Act: -0.0000

Data Index: 206877 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0121. Min Act: -0.0000

Data Index: 827013 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1797302 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1160610 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9478. Min Act: -0.0000

Data Index: 896871 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1865472 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9530. Min Act: -0.0000

Data Index: 343138 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.0145. Min Act: -0.0000

Data Index: 748517 (The Pile)

Max Activating Token Index: 584