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

Dataset: The Pile

Neuron 2481 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: 1.2610. Min Range: -1.2610

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1439338 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.2246. Min Act: -0.0000

Data Index: 984749 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.2501. Min Act: -0.0000

Data Index: 626964 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.2079. Min Act: -0.0000

Data Index: 17288 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1658087 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.1041. Min Act: -0.0000

Data Index: 328264 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0922. Min Act: -0.0000

Data Index: 213530 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1196292 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1321905 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0870. Min Act: -0.0000

Data Index: 484505 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1678797 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1385817 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0742. Min Act: -0.0000

Data Index: 694484 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1077651 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0670. Min Act: -0.0000

Data Index: 80278 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0948. Min Act: -0.0000

Data Index: 183118 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0569. Min Act: -0.0000

Data Index: 150938 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0200. Min Act: -0.0000

Data Index: 657774 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1149957 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0126. Min Act: -0.0000

Data Index: 59682 (The Pile)

Max Activating Token Index: 449