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

Dataset: The Pile

Neuron 2766 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.4400. Min Act: -0.0000

Data Index: 180916 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.3024. Min Act: -0.0000

Data Index: 162901 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1845256 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1462204 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0744. Min Act: -0.0000

Data Index: 935032 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1789. Min Act: -0.0000

Data Index: 457063 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1015. Min Act: -0.0000

Data Index: 186869 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1724. Min Act: -0.0000

Data Index: 815155 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1535. Min Act: -0.0000

Data Index: 171744 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1946. Min Act: -0.0000

Data Index: 890150 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1043439 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1286836 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1136085 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0216. Min Act: -0.0000

Data Index: 164474 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1968890 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0674. Min Act: -0.0000

Data Index: 330740 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.1859. Min Act: -0.0000

Data Index: 737606 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0023. Min Act: -0.0000

Data Index: 448600 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1508444 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 1.4400. Min Range: -1.4400

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1642284 (The Pile)

Max Activating Token Index: 783