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

Dataset: The Pile

Neuron 28 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: 1.0069. Min Range: -1.0069

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1231066 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 1.0069. Min Range: -1.0069

Max Act: 1.0069. Min Act: -0.0000

Data Index: 501689 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1740945 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1259193 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1531492 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1714670 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7844. Min Act: -0.0000

Data Index: 440305 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7769. Min Act: -0.0000

Data Index: 686549 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1771651 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1716251 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7345. Min Act: -0.0000

Data Index: 901977 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7794. Min Act: -0.0000

Data Index: 947942 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7492. Min Act: -0.0000

Data Index: 215994 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7435. Min Act: -0.0000

Data Index: 877505 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7350. Min Act: -0.0000

Data Index: 856294 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1865186 (The Pile)

Max Activating Token Index: 119

Text #16

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7237. Min Act: -0.0000

Data Index: 441537 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7121. Min Act: -0.0000

Data Index: 836607 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1676675 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.6931. Min Act: -0.0000

Data Index: 810427 (The Pile)

Max Activating Token Index: 856