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

Dataset: The Pile

Neuron 2023 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1149852 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5544. Min Act: -0.0000

Data Index: 56780 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1256437 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5738. Min Act: -0.0000

Data Index: 261217 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1942095 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5713. Min Act: -0.0000

Data Index: 39302 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5276. Min Act: -0.0000

Data Index: 334976 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1570100 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5772. Min Act: -0.0000

Data Index: 595149 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1133318 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1959547 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4936. Min Act: -0.0000

Data Index: 830784 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5433. Min Act: -0.0000

Data Index: 460272 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1252080 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1070404 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1573355 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1942724 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1095644 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5026. Min Act: -0.0000

Data Index: 746149 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5161. Min Act: -0.0000

Data Index: 323296 (The Pile)

Max Activating Token Index: 509