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

Dataset: The Pile

Neuron 33 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: 0.8282. Min Range: -0.8282

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1467152 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7714. Min Act: -0.0000

Data Index: 528001 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7568. Min Act: -0.0000

Data Index: 270180 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7228. Min Act: -0.0000

Data Index: 292121 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1291909 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7234. Min Act: -0.0000

Data Index: 167832 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7619. Min Act: -0.0000

Data Index: 759468 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6902. Min Act: -0.0000

Data Index: 308735 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1551946 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1360754 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1199936 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6593. Min Act: -0.0000

Data Index: 361160 (The Pile)

Max Activating Token Index: 839

Text #13

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6843. Min Act: -0.0000

Data Index: 103895 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1063493 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1952786 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1297535 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1194695 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6297. Min Act: -0.0000

Data Index: 408928 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6105. Min Act: -0.0000

Data Index: 162300 (The Pile)

Max Activating Token Index: 847