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

Dataset: The Pile

Neuron 2370 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: 0.8198. Min Range: -0.8198

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1985294 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.8131. Min Act: -0.0000

Data Index: 130562 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1371921 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1073348 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.7226. Min Act: -0.0000

Data Index: 481467 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.7233. Min Act: -0.0000

Data Index: 624893 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1852426 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1589520 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1248662 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6499. Min Act: -0.0000

Data Index: 681437 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5581. Min Act: -0.0000

Data Index: 273513 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6872. Min Act: -0.0000

Data Index: 830375 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5548. Min Act: -0.0000

Data Index: 49302 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6271. Min Act: -0.0000

Data Index: 776425 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1866655 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5653. Min Act: -0.0000

Data Index: 187550 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1372004 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1055804 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1475871 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.8198. Min Range: -0.8198

Max Act: 0.4920. Min Act: -0.0000

Data Index: 687569 (The Pile)

Max Activating Token Index: 149