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

Dataset: The Pile

Neuron 861 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1644515 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4306. Min Act: -0.0000

Data Index: 83386 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1415789 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3739. Min Act: -0.0000

Data Index: 260671 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1751636 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3581. Min Act: -0.0000

Data Index: 993 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1021455 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1145261 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1887260 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3618. Min Act: -0.0000

Data Index: 893170 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1426138 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3530. Min Act: -0.0000

Data Index: 757820 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3486. Min Act: -0.0000

Data Index: 276133 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1728565 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1562900 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3343. Min Act: -0.0000

Data Index: 131861 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3281. Min Act: -0.0000

Data Index: 662805 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3109. Min Act: -0.0000

Data Index: 742689 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1843782 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3335. Min Act: -0.0000

Data Index: 908222 (The Pile)

Max Activating Token Index: 575