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

Dataset: The Pile

Neuron 1938 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: 0.7534. Min Range: -0.7534

Max Act: 0.7534. Min Act: -0.0000

Data Index: 201990 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1496226 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6756. Min Act: -0.0000

Data Index: 270711 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1614230 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1418981 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1510868 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6430. Min Act: -0.0000

Data Index: 343746 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6254. Min Act: -0.0000

Data Index: 306909 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1646768 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1743674 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1682322 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1749588 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1090380 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1131452 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5918. Min Act: -0.0000

Data Index: 998290 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5543. Min Act: -0.0000

Data Index: 512340 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5938. Min Act: -0.0000

Data Index: 32680 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5817. Min Act: -0.0000

Data Index: 72876 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1837821 (The Pile)

Max Activating Token Index: 548