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

Dataset: The Pile

Neuron 2688 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5294. Min Range: -5.5294

Max Act: 5.5294. Min Act: -0.0000

Data Index: 959737 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.7837. Min Act: -0.0000

Data Index: 279121 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.3951. Min Act: -0.0000

Data Index: 1092993 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.2457. Min Act: -0.0000

Data Index: 1011539 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.5678. Min Act: -0.0000

Data Index: 405572 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.3398. Min Act: -0.0000

Data Index: 523843 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.2816. Min Act: -0.0000

Data Index: 341942 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.1008. Min Act: -0.0000

Data Index: 160545 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.9724. Min Act: -0.0000

Data Index: 159864 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.9425. Min Act: -0.0000

Data Index: 563169 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.5380. Min Act: -0.0000

Data Index: 1346942 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.4762. Min Act: -0.0000

Data Index: 1877249 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.4106. Min Act: -0.0000

Data Index: 587834 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 5.5294. Min Range: -5.5294

Max Act: 4.0467. Min Act: -0.0000

Data Index: 342 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.2223. Min Act: -0.0000

Data Index: 1633034 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.5283. Min Act: -0.0000

Data Index: 176984 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.5155. Min Act: -0.0000

Data Index: 594999 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.6539. Min Act: -0.0000

Data Index: 996550 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.7793. Min Act: -0.0000

Data Index: 288156 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 5.5294. Min Range: -5.5294

Max Act: 3.2661. Min Act: -0.0000

Data Index: 1177493 (The Pile)

Max Activating Token Index: 42