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

Dataset: The Pile

Neuron 4146 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: 5.7337. Min Range: -5.7337

Max Act: 5.7337. Min Act: -0.0000

Data Index: 1738056 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.4995. Min Act: -0.0000

Data Index: 156969 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.1124. Min Act: -0.0000

Data Index: 96498 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.5513. Min Act: -0.0000

Data Index: 573690 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.9172. Min Act: -0.0000

Data Index: 674465 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.5378. Min Act: -0.0000

Data Index: 1899809 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.0046. Min Act: -0.0000

Data Index: 1116221 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.2625. Min Act: -0.0000

Data Index: 390060 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.5412. Min Act: -0.0000

Data Index: 868380 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.5305. Min Act: -0.0000

Data Index: 1541990 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.2084. Min Act: -0.0000

Data Index: 531724 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.3605. Min Act: -0.0000

Data Index: 1765330 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.2130. Min Act: -0.0000

Data Index: 1920469 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.5237. Min Act: -0.0000

Data Index: 1735857 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 5.7337. Min Range: -5.7337

Max Act: 3.8659. Min Act: -0.0000

Data Index: 1001057 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.3577. Min Act: -0.0000

Data Index: 1750323 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.0953. Min Act: -0.0000

Data Index: 1412676 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 5.7337. Min Range: -5.7337

Max Act: 4.0772. Min Act: -0.0000

Data Index: 222303 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 5.7337. Min Range: -5.7337

Max Act: 3.8716. Min Act: -0.0000

Data Index: 1188423 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 5.7337. Min Range: -5.7337

Max Act: 3.7416. Min Act: -0.0000

Data Index: 332372 (The Pile)

Max Activating Token Index: 855