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

Dataset: The Pile

Neuron 1357 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1656602 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1887699 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1252391 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1601497 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.0641. Min Range: -1.0641

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1065506 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1844219 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.9306. Min Act: -0.0000

Data Index: 637258 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1009185 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1703060 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1621460 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1771900 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1134340 (The Pile)

Max Activating Token Index: 928

Text #12

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1304834 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1090873 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8263. Min Act: -0.0000

Data Index: 717250 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1482431 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1036886 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1585961 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.7909. Min Act: -0.0000

Data Index: 380725 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.0641. Min Range: -1.0641

Max Act: 0.8663. Min Act: -0.0000

Data Index: 622082 (The Pile)

Max Activating Token Index: 505