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

Dataset: The Pile

Neuron 205 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: 0.8409. Min Range: -0.8409

Max Act: 0.8409. Min Act: -0.0000

Data Index: 988052 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7733. Min Act: -0.0000

Data Index: 936358 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1602731 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7090. Min Act: -0.0000

Data Index: 374160 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1195919 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6365. Min Act: -0.0000

Data Index: 548471 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1824109 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6002. Min Act: -0.0000

Data Index: 200299 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5554. Min Act: -0.0000

Data Index: 398724 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1321290 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5659. Min Act: -0.0000

Data Index: 935382 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1733485 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5704. Min Act: -0.0000

Data Index: 844129 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1643941 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5599. Min Act: -0.0000

Data Index: 233188 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5532. Min Act: -0.0000

Data Index: 634098 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1026301 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5750. Min Act: -0.0000

Data Index: 527262 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5380. Min Act: -0.0000

Data Index: 542744 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5747. Min Act: -0.0000

Data Index: 236617 (The Pile)

Max Activating Token Index: 612