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

Dataset: The Pile

Neuron 811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1191449 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1793595 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1071. Min Act: -0.0000

Data Index: 271317 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1638771 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1068304 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0982. Min Act: -0.0000

Data Index: 205343 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0913. Min Act: -0.0000

Data Index: 375086 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0930. Min Act: -0.0000

Data Index: 775665 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0833. Min Act: -0.0000

Data Index: 936071 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0853. Min Act: -0.0000

Data Index: 191076 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1438005 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1706900 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1218786 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0815. Min Act: -0.0000

Data Index: 205388 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0720. Min Act: -0.0000

Data Index: 107816 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0838. Min Act: -0.0000

Data Index: 140983 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0746. Min Act: -0.0000

Data Index: 70055 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1042741 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0683. Min Act: -0.0000

Data Index: 950654 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1275588 (The Pile)

Max Activating Token Index: 789