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

Dataset: The Pile

Neuron 1115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1519101 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7779. Min Act: -0.0000

Data Index: 345978 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7560. Min Act: -0.0000

Data Index: 759656 (The Pile)

Max Activating Token Index: 851

Text #3

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7630. Min Act: -0.0000

Data Index: 367521 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6742. Min Act: -0.0000

Data Index: 854725 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7094. Min Act: -0.0000

Data Index: 825554 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6822. Min Act: -0.0000

Data Index: 600787 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1963280 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1180099 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6699. Min Act: -0.0000

Data Index: 678957 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1080129 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1266500 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1872146 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6592. Min Act: -0.0000

Data Index: 81868 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.5935. Min Act: -0.0000

Data Index: 51520 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6333. Min Act: -0.0000

Data Index: 834187 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1029734 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1475901 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1327868 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6407. Min Act: -0.0000

Data Index: 608813 (The Pile)

Max Activating Token Index: 812