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

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

Neuron 4245 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.3222. Min Act: -0.0003

Data Index: 130100 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.2303. Min Act: -0.0003

Data Index: 508922 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.2280. Min Act: -0.0002

Data Index: 877320 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1912. Min Act: -0.0003

Data Index: 381299 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1706. Min Act: -0.0003

Data Index: 789693 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1711. Min Act: -0.0003

Data Index: 144872 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1640. Min Act: -0.0003

Data Index: 397270 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0938. Min Act: -0.0003

Data Index: 704298 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1623. Min Act: -0.0003

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1446. Min Act: -0.0003

Data Index: 386766 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1455. Min Act: -0.0002

Data Index: 823247 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1241. Min Act: -0.0003

Data Index: 131660 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1071. Min Act: -0.0002

Data Index: 770461 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1464. Min Act: -0.0003

Data Index: 361203 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0729. Min Act: -0.0003

Data Index: 1191797 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1009. Min Act: -0.0003

Data Index: 388039 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0677. Min Act: -0.0003

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.1018. Min Act: -0.0003

Data Index: 877862 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0552. Min Act: -0.0003

Data Index: 96210 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.3222. Min Range: -1.3222

Max Act: 1.0882. Min Act: -0.0002

Data Index: 1253412 (C4 (Web Text))

Max Activating Token Index: 92