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

Dataset: The Pile

Neuron 1699 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: 1.0465. Min Range: -1.0465

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1937370 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1198663 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7303. Min Act: -0.0000

Data Index: 816398 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7702. Min Act: -0.0000

Data Index: 857143 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1440666 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8269. Min Act: -0.0000

Data Index: 53486 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1745937 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1433452 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7402. Min Act: -0.0000

Data Index: 805282 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6472. Min Act: -0.0000

Data Index: 939019 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1625389 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6269. Min Act: -0.0000

Data Index: 887603 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7232. Min Act: -0.0000

Data Index: 554164 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1038257 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1487747 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1456429 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5902. Min Act: -0.0000

Data Index: 93264 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1406908 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6228. Min Act: -0.0000

Data Index: 357860 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6152. Min Act: -0.0000

Data Index: 755410 (The Pile)

Max Activating Token Index: 802