Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7094. Min Act: -0.0001

Data Index: 1642725 (Python Code)

Max Activating Token Index: 332

Text #1

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.8891. Min Act: -0.0001

Data Index: 919907 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7767. Min Act: -0.0001

Data Index: 686275 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7200. Min Act: -0.0001

Data Index: 66619 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7190. Min Act: -0.0001

Data Index: 1161860 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7063. Min Act: -0.0001

Data Index: 404241 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5437. Min Act: -0.0001

Data Index: 49209 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4557. Min Act: -0.0001

Data Index: 139496 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.9331. Min Act: -0.0001

Data Index: 1004677 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6153. Min Act: -0.0001

Data Index: 1112751 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7744. Min Act: -0.0001

Data Index: 1072390 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6179. Min Act: -0.0001

Data Index: 1348083 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7653. Min Act: -0.0001

Data Index: 917382 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4961. Min Act: -0.0001

Data Index: 943481 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6373. Min Act: -0.0001

Data Index: 1281391 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6629. Min Act: -0.0001

Data Index: 845159 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6768. Min Act: -0.0001

Data Index: 1450197 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4904. Min Act: -0.0001

Data Index: 653218 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5932. Min Act: -0.0001

Data Index: 179094 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5961. Min Act: -0.0001

Data Index: 111271 (C4 (Web Text))

Max Activating Token Index: 774