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

Dataset: The Pile

Neuron 1850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.8191. Min Act: -0.0000

Data Index: 1877002 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7396. Min Act: -0.0000

Data Index: 1937721 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1059093 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7484. Min Act: -0.0000

Data Index: 1165926 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7301. Min Act: -0.0000

Data Index: 781997 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6240. Min Act: -0.0000

Data Index: 150723 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7240. Min Act: -0.0000

Data Index: 258382 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1773881 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6287. Min Act: -0.0000

Data Index: 559532 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6758. Min Act: -0.0000

Data Index: 754742 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1237015 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5626. Min Act: -0.0000

Data Index: 46415 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4632. Min Act: -0.0000

Data Index: 1395376 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1762171 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4967. Min Act: -0.0000

Data Index: 63154 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4924. Min Act: -0.0000

Data Index: 470137 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4735. Min Act: -0.0000

Data Index: 666003 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1696315 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4729. Min Act: -0.0000

Data Index: 849384 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4681. Min Act: -0.0000

Data Index: 713443 (The Pile)

Max Activating Token Index: 534