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

Dataset: The Pile

Neuron 896 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: 1.7286. Min Range: -1.7286

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1973088 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.1855. Min Act: 0.0000

Data Index: 1805727 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.7286. Min Range: -1.7286

Max Act: 1.1505. Min Act: -0.0000

Data Index: 715556 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1096324 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1008120 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.8331. Min Act: -0.0000

Data Index: 447320 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.7500. Min Act: -0.0000

Data Index: 28720 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1856472 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.7247. Min Act: -0.0000

Data Index: 778627 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.7116. Min Act: -0.0000

Data Index: 712875 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6683. Min Act: -0.0000

Data Index: 592419 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6544. Min Act: 0.0000

Data Index: 636887 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.5763. Min Act: -0.0000

Data Index: 112076 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6355. Min Act: -0.0000

Data Index: 969041 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1199196 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6503. Min Act: -0.0000

Data Index: 436395 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1918762 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6961. Min Act: -0.0000

Data Index: 713199 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1700595 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.7286. Min Range: -1.7286

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1241456 (The Pile)

Max Activating Token Index: 810