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

Dataset: The Pile

Neuron 3110 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: 0.7674. Min Range: -0.7674

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1857579 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1917944 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5968. Min Act: -0.0000

Data Index: 618012 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1386792 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1570503 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1528834 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1106978 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5305. Min Act: -0.0000

Data Index: 362135 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1609102 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1606938 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1086037 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5083. Min Act: -0.0000

Data Index: 898295 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5464. Min Act: -0.0000

Data Index: 499654 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1175343 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1830402 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5376. Min Act: -0.0000

Data Index: 950794 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1899832 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5267. Min Act: -0.0000

Data Index: 708585 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1267316 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5242. Min Act: -0.0000

Data Index: 305891 (The Pile)

Max Activating Token Index: 233