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

Dataset: The Pile

Neuron 2004 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: 0.4985. Min Range: -0.4985

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1414677 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1729689 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1470384 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3400. Min Act: -0.0000

Data Index: 731288 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1369307 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3798. Min Act: -0.0000

Data Index: 579765 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3205. Min Act: -0.0000

Data Index: 885491 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1415047 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1344590 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2970. Min Act: 0.0000

Data Index: 304338 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1378950 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2801. Min Act: -0.0000

Data Index: 478767 (The Pile)

Max Activating Token Index: 349

Text #12

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2995. Min Act: -0.0000

Data Index: 774012 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2875. Min Act: 0.0000

Data Index: 1000759 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1638637 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2576. Min Act: -0.0000

Data Index: 244719 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2636. Min Act: -0.0000

Data Index: 574067 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2807. Min Act: -0.0000

Data Index: 805361 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2680. Min Act: -0.0000

Data Index: 665611 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.4985. Min Range: -0.4985

Max Act: 0.2835. Min Act: -0.0000

Data Index: 225314 (The Pile)

Max Activating Token Index: 178