Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.8378. Min Act: -0.0001

Data Index: 643357 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.4699. Min Act: -0.0001

Data Index: 1176748 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2976. Min Act: -0.0001

Data Index: 480290 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.4256. Min Act: -0.0002

Data Index: 1080690 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.3799. Min Act: -0.0002

Data Index: 835316 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.3020. Min Act: -0.0001

Data Index: 884534 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2008. Min Act: -0.0001

Data Index: 936317 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2770. Min Act: -0.0002

Data Index: 1357490 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2325. Min Act: -0.0001

Data Index: 918078 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.1707. Min Act: -0.0002

Data Index: 1232804 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.1893. Min Act: -0.0002

Data Index: 403753 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.1020. Min Act: -0.0002

Data Index: 499441 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.0937. Min Act: -0.0002

Data Index: 1000520 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.1158. Min Act: -0.0001

Data Index: 22149 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2536. Min Act: -0.0001

Data Index: 530405 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.2432. Min Act: -0.0001

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.0954. Min Act: -0.0001

Data Index: 481405 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.1370. Min Act: -0.0002

Data Index: 844267 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.0962. Min Act: -0.0001

Data Index: 278143 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.8378. Min Range: -1.8378

Max Act: 1.0757. Min Act: -0.0002

Data Index: 271075 (C4 (Web Text))

Max Activating Token Index: 679