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

Dataset: The Pile

Neuron 188 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.8530. Min Act: -0.0000

Data Index: 154501 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1859786 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1506504 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6188. Min Act: -0.0000

Data Index: 775415 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1397029 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6083. Min Act: -0.0000

Data Index: 107382 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5742. Min Act: -0.0000

Data Index: 998575 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6444. Min Act: -0.0000

Data Index: 979455 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5283. Min Act: -0.0000

Data Index: 508115 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5265. Min Act: -0.0000

Data Index: 198062 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4758. Min Act: -0.0000

Data Index: 575828 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1525979 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1937158 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4020. Min Act: -0.0000

Data Index: 706366 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.2908. Min Act: -0.0000

Data Index: 539186 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1710410 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.3457. Min Act: 0.0000

Data Index: 371550 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.3352. Min Act: 0.0000

Data Index: 1669756 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.3118. Min Act: 0.0000

Data Index: 739780 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4224. Min Act: -0.0000

Data Index: 156593 (The Pile)

Max Activating Token Index: 832