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

Dataset: The Pile

Neuron 2315 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: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1572639 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6823. Min Act: -0.0000

Data Index: 647624 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1290993 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1707159 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1941626 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1103859 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5882. Min Act: -0.0000

Data Index: 14616 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1277791 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5677. Min Act: -0.0000

Data Index: 521487 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1121677 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1954938 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1051312 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4532. Min Act: -0.0000

Data Index: 637041 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4558. Min Act: -0.0000

Data Index: 227728 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4985. Min Act: -0.0000

Data Index: 343767 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1972573 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4857. Min Act: -0.0000

Data Index: 234827 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.3891. Min Act: -0.0000

Data Index: 785528 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1963402 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1577222 (The Pile)

Max Activating Token Index: 731