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

Dataset: The Pile

Neuron 3117 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: 1.3857. Min Range: -1.3857

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1993129 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1257389 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9647. Min Act: 0.0000

Data Index: 1650705 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9524. Min Act: -0.0000

Data Index: 46732 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1895216 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1555437 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8433. Min Act: -0.0000

Data Index: 202064 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1259086 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1942690 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8342. Min Act: -0.0000

Data Index: 450256 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8550. Min Act: -0.0000

Data Index: 469676 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8183. Min Act: 0.0000

Data Index: 617026 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8185. Min Act: -0.0000

Data Index: 846961 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1981576 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1083439 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1011399 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1514274 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7692. Min Act: 0.0000

Data Index: 1081508 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7767. Min Act: 0.0000

Data Index: 1320728 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1992263 (The Pile)

Max Activating Token Index: 925