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

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

Neuron 443 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2660. Min Act: -0.0000

Data Index: 289476 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2224. Min Act: -0.0000

Data Index: 416365 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.3300. Min Act: -0.0000

Data Index: 214464 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2838. Min Act: -0.0000

Data Index: 97468 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2291. Min Act: -0.0000

Data Index: 898562 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1446. Min Act: -0.0000

Data Index: 479246 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1102. Min Act: -0.0000

Data Index: 815971 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0887. Min Act: -0.0000

Data Index: 988773 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1511. Min Act: -0.0000

Data Index: 195862 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1506. Min Act: -0.0000

Data Index: 139986 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1102636 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1873. Min Act: -0.0000

Data Index: 289734 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0789. Min Act: -0.0000

Data Index: 150845 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0767. Min Act: -0.0000

Data Index: 793359 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1224. Min Act: -0.0000

Data Index: 21683 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0788. Min Act: -0.0000

Data Index: 603041 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1356. Min Act: -0.0000

Data Index: 627976 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1005. Min Act: -0.0000

Data Index: 436323 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0367. Min Act: -0.0000

Data Index: 567420 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1347166 (C4 (Web Text))

Max Activating Token Index: 169