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

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

Neuron 4332 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.9699. Min Act: -0.0000

Data Index: 218576 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.6400. Min Act: -0.0000

Data Index: 1068180 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.4389. Min Act: -0.0000

Data Index: 1280699 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.5199. Min Act: -0.0000

Data Index: 475466 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.4583. Min Act: -0.0000

Data Index: 273123 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.3010. Min Act: -0.0000

Data Index: 1294124 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.2653. Min Act: -0.0000

Data Index: 551229 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1168872 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.1006. Min Act: -0.0000

Data Index: 519638 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.3055. Min Act: -0.0000

Data Index: 172769 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.0179. Min Act: -0.0000

Data Index: 17920 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.1241. Min Act: -0.0000

Data Index: 320212 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.2349. Min Act: -0.0000

Data Index: 1124418 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.0493. Min Act: -0.0000

Data Index: 143513 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.0340. Min Act: -0.0000

Data Index: 200006 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1183829 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 2.9699. Min Range: -2.9699

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1150749 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.0060. Min Act: -0.0000

Data Index: 270541 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.9699. Min Range: -2.9699

Max Act: 1.9868. Min Act: -0.0000

Data Index: 655435 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 2.9699. Min Range: -2.9699

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1100069 (C4 (Web Text))

Max Activating Token Index: 728