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

Dataset: The Pile

Neuron 787 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: 3.6427. Min Range: -3.6427

Max Act: 3.6427. Min Act: -0.0000

Data Index: 312554 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 3.6427. Min Range: -3.6427

Max Act: 3.0276. Min Act: -0.0000

Data Index: 303972 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 3.6427. Min Range: -3.6427

Max Act: 3.4630. Min Act: -0.0000

Data Index: 1932092 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 3.6427. Min Range: -3.6427

Max Act: 3.0176. Min Act: -0.0000

Data Index: 1212732 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.9316. Min Act: -0.0000

Data Index: 316395 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 3.6427. Min Range: -3.6427

Max Act: 3.0321. Min Act: -0.0000

Data Index: 1184091 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.8501. Min Act: -0.0000

Data Index: 900001 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.5263. Min Act: -0.0000

Data Index: 1547048 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.7845. Min Act: -0.0000

Data Index: 407418 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.7210. Min Act: 0.0000

Data Index: 300850 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.5644. Min Act: -0.0000

Data Index: 1888116 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.6398. Min Act: -0.0000

Data Index: 1982993 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.5408. Min Act: 0.0000

Data Index: 1376814 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.6872. Min Act: -0.0000

Data Index: 350199 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.4090. Min Act: -0.0000

Data Index: 525703 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1068420 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.5012. Min Act: -0.0000

Data Index: 1575203 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.4947. Min Act: -0.0000

Data Index: 912479 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.6458. Min Act: -0.0000

Data Index: 527816 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 3.6427. Min Range: -3.6427

Max Act: 2.6238. Min Act: -0.0000

Data Index: 1047009 (The Pile)

Max Activating Token Index: 280