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

Dataset: The Pile

Neuron 4207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1170. Min Range: -1.1170

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1287039 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.8975. Min Act: -0.0000

Data Index: 113297 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1198287 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7918. Min Act: -0.0000

Data Index: 938912 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1061231 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1640164 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1823504 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1602055 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1172023 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7689. Min Act: -0.0000

Data Index: 693495 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7203. Min Act: -0.0000

Data Index: 368106 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7249. Min Act: -0.0000

Data Index: 575650 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1204826 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7057. Min Act: -0.0000

Data Index: 14948 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1831945 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.7419. Min Act: -0.0000

Data Index: 336081 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6557. Min Act: -0.0000

Data Index: 288867 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1867313 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1226874 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.1170. Min Range: -1.1170

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1939615 (The Pile)

Max Activating Token Index: 44