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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3130 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1009794 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.3832. Min Act: -0.0000

Data Index: 145436 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.3943. Min Act: -0.0000

Data Index: 610942 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.3803. Min Act: -0.0000

Data Index: 325088 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1319644 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2632. Min Act: -0.0000

Data Index: 599481 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2092. Min Act: -0.0001

Data Index: 556914 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2027. Min Act: -0.0000

Data Index: 1291548 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2099. Min Act: -0.0000

Data Index: 929635 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2890. Min Act: -0.0000

Data Index: 299253 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1706. Min Act: -0.0000

Data Index: 712368 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1134. Min Act: -0.0000

Data Index: 14152 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.2137. Min Act: -0.0001

Data Index: 217272 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.0225. Min Act: -0.0000

Data Index: 155457 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1979. Min Act: -0.0000

Data Index: 57502 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1251. Min Act: -0.0000

Data Index: 930406 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.0493. Min Act: -0.0000

Data Index: 517030 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1562. Min Act: -0.0000

Data Index: 355255 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1229912 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.4306. Min Range: -1.4306

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1338494 (C4 (Web Text))

Max Activating Token Index: 823