Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1250494 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.7227. Min Act: -0.0000

Data Index: 474123 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1199747 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1519470 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5502. Min Act: -0.0000

Data Index: 824985 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5982. Min Act: -0.0000

Data Index: 780766 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5864. Min Act: -0.0000

Data Index: 215803 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5514. Min Act: -0.0000

Data Index: 261171 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1684714 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1497091 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1164374 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1184811 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5402. Min Act: -0.0000

Data Index: 694049 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1220730 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1780372 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1355755 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5252. Min Act: -0.0000

Data Index: 607254 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5307. Min Act: -0.0000

Data Index: 585650 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1674850 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.7227. Min Range: -0.7227

Max Act: 0.5619. Min Act: -0.0000

Data Index: 661182 (The Pile)

Max Activating Token Index: 90