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

Dataset: The Pile

Neuron 3252 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: 0.8034. Min Range: -0.8034

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1188847 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7680. Min Act: -0.0000

Data Index: 342369 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1939535 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7675. Min Act: -0.0000

Data Index: 690026 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7439. Min Act: -0.0000

Data Index: 856142 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1085580 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7603. Min Act: -0.0000

Data Index: 197460 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1926941 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1823662 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1597915 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1674683 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1474917 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1744936 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6669. Min Act: -0.0000

Data Index: 834588 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6931. Min Act: -0.0000

Data Index: 403133 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6248. Min Act: -0.0000

Data Index: 85110 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6573. Min Act: -0.0000

Data Index: 743321 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1612860 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6221. Min Act: -0.0000

Data Index: 730327 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1365616 (The Pile)

Max Activating Token Index: 850