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

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

Neuron 1207 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: 3.7116. Min Range: -3.7116

Max Act: 3.7116. Min Act: -0.0000

Data Index: 962875 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.2708. Min Act: -0.0000

Data Index: 128873 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 3.7116. Min Range: -3.7116

Max Act: 3.1736. Min Act: -0.0001

Data Index: 837169 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.9585. Min Act: -0.0000

Data Index: 840633 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.8199. Min Act: -0.0000

Data Index: 77239 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.8090. Min Act: -0.0000

Data Index: 654086 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.7011. Min Act: -0.0000

Data Index: 627319 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.8348. Min Act: -0.0000

Data Index: 43665 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.6652. Min Act: -0.0000

Data Index: 1245137 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.6683. Min Act: -0.0000

Data Index: 780489 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.9306. Min Act: -0.0000

Data Index: 527790 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.7589. Min Act: -0.0000

Data Index: 1279404 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.6020. Min Act: -0.0000

Data Index: 350908 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.8630. Min Act: -0.0000

Data Index: 413922 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.8402. Min Act: -0.0000

Data Index: 296728 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.6914. Min Act: -0.0001

Data Index: 794425 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.5476. Min Act: -0.0000

Data Index: 319118 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.6688. Min Act: -0.0000

Data Index: 1272209 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.5081. Min Act: -0.0001

Data Index: 73821 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 3.7116. Min Range: -3.7116

Max Act: 2.7576. Min Act: -0.0000

Data Index: 1060635 (C4 (Web Text))

Max Activating Token Index: 288