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

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

Neuron 2272 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.8341. Min Act: 0.0002

Data Index: 1144378 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1141332 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7762. Min Act: -0.0000

Data Index: 796013 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.8102. Min Act: -0.0000

Data Index: 180857 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7880. Min Act: -0.0000

Data Index: 794411 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7460. Min Act: 0.0001

Data Index: 411189 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6919. Min Act: -0.0000

Data Index: 580101 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7289. Min Act: 0.0000

Data Index: 875762 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7139. Min Act: -0.0000

Data Index: 330831 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7290. Min Act: 0.0000

Data Index: 1074622 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7206. Min Act: 0.0001

Data Index: 1089257 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6785. Min Act: -0.0000

Data Index: 504058 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6916. Min Act: 0.0000

Data Index: 241400 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7014. Min Act: -0.0000

Data Index: 806103 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6771. Min Act: -0.0000

Data Index: 915915 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.7260. Min Act: -0.0000

Data Index: 196718 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6380. Min Act: 0.0000

Data Index: 429725 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6275. Min Act: -0.0000

Data Index: 746387 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6659. Min Act: -0.0000

Data Index: 253799 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.6366. Min Act: -0.0000

Data Index: 113998 (C4 (Web Text))

Max Activating Token Index: 386