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

Dataset: The Pile

Neuron 3606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1248. Min Range: -5.1248

Max Act: 5.1248. Min Act: -0.0000

Data Index: 1993181 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.6917. Min Act: -0.0000

Data Index: 1828845 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.6914. Min Act: -0.0000

Data Index: 1177713 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.4606. Min Act: -0.0000

Data Index: 382956 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.3674. Min Act: -0.0000

Data Index: 974640 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.4764. Min Act: -0.0000

Data Index: 830733 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.4168. Min Act: -0.0000

Data Index: 887238 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.2063. Min Act: -0.0000

Data Index: 1745171 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.9841. Min Act: -0.0000

Data Index: 1727215 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.3218. Min Act: -0.0000

Data Index: 431451 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.3215. Min Act: -0.0000

Data Index: 1217744 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.2674. Min Act: -0.0000

Data Index: 211553 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.0796. Min Act: -0.0000

Data Index: 1409493 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.8185. Min Act: -0.0000

Data Index: 1427048 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 5.1248. Min Range: -5.1248

Max Act: 4.1309. Min Act: -0.0000

Data Index: 1584975 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.5628. Min Act: -0.0000

Data Index: 1109361 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.8593. Min Act: -0.0000

Data Index: 944814 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.8647. Min Act: -0.0000

Data Index: 1588443 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.6700. Min Act: -0.0000

Data Index: 828114 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 5.1248. Min Range: -5.1248

Max Act: 3.8160. Min Act: -0.0000

Data Index: 1365971 (The Pile)

Max Activating Token Index: 210