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

Dataset: The Pile

Neuron 3796 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4877. Min Act: -0.0000

Data Index: 434105 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1991595 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3623. Min Act: -0.0000

Data Index: 282536 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2528. Min Act: -0.0000

Data Index: 764523 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4820. Min Act: -0.0000

Data Index: 990958 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1370313 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1683671 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2803. Min Act: -0.0000

Data Index: 522498 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3066. Min Act: -0.0000

Data Index: 251128 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3708. Min Act: -0.0000

Data Index: 807128 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4777. Min Act: -0.0000

Data Index: 124232 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1537256 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2948. Min Act: -0.0000

Data Index: 382289 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2873. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1496381 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2144. Min Act: -0.0000

Data Index: 559777 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1154440 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2719. Min Act: -0.0000

Data Index: 645723 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1485. Min Act: -0.0000

Data Index: 670311 (The Pile)

Max Activating Token Index: 967