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

Dataset: The Pile

Neuron 3828 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: 3.3902. Min Range: -3.3902

Max Act: 3.3902. Min Act: -0.0000

Data Index: 535468 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3007. Min Act: -0.0000

Data Index: 338471 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2919. Min Act: -0.0000

Data Index: 777958 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.1676. Min Act: -0.0000

Data Index: 1413269 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.1538. Min Act: -0.0000

Data Index: 1505350 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.9661. Min Act: -0.0000

Data Index: 490697 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2667. Min Act: -0.0000

Data Index: 91562 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.0915. Min Act: -0.0000

Data Index: 1971984 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.0491. Min Act: -0.0000

Data Index: 1238987 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.0663. Min Act: -0.0000

Data Index: 742552 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.1668. Min Act: -0.0000

Data Index: 284667 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.8801. Min Act: -0.0000

Data Index: 1999469 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.1320. Min Act: -0.0000

Data Index: 1612929 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.7180. Min Act: -0.0000

Data Index: 1589940 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.6280. Min Act: -0.0000

Data Index: 1251345 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.9953. Min Act: -0.0000

Data Index: 298510 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.9323. Min Act: -0.0000

Data Index: 1360061 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.6685. Min Act: -0.0000

Data Index: 803968 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.9419. Min Act: -0.0000

Data Index: 1322359 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 3.3902. Min Range: -3.3902

Max Act: 2.9285. Min Act: -0.0000

Data Index: 1279372 (The Pile)

Max Activating Token Index: 309