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

Dataset: The Pile

Neuron 3033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0762. Min Range: -1.0762

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1920612 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1793907 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7903. Min Act: -0.0000

Data Index: 180193 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7968. Min Act: -0.0000

Data Index: 498401 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1443933 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1659245 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7254. Min Act: -0.0000

Data Index: 710078 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1387130 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6952. Min Act: -0.0000

Data Index: 31286 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1503878 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6864. Min Act: -0.0000

Data Index: 920823 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1882210 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6553. Min Act: -0.0000

Data Index: 260465 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6486. Min Act: -0.0000

Data Index: 684722 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1239311 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6998. Min Act: -0.0000

Data Index: 237507 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1226808 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6505. Min Act: -0.0000

Data Index: 532578 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6458. Min Act: -0.0000

Data Index: 544392 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.0762. Min Range: -1.0762

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1209625 (The Pile)

Max Activating Token Index: 959