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

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

Neuron 5316 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.3697. Min Act: -0.0000

Data Index: 422267 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.4067. Min Act: -0.0000

Data Index: 858905 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.2499. Min Act: -0.0000

Data Index: 18352 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.1331. Min Act: -0.0000

Data Index: 670474 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.4067. Min Range: -1.4067

Max Act: 1.0967. Min Act: -0.0000

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9573. Min Act: 0.0000

Data Index: 933222 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8940. Min Act: 0.0000

Data Index: 792327 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.9802. Min Act: -0.0000

Data Index: 822424 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8998. Min Act: -0.0000

Data Index: 871704 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8152. Min Act: -0.0000

Data Index: 100457 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8683. Min Act: 0.0000

Data Index: 1135279 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8595. Min Act: -0.0000

Data Index: 694027 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8314. Min Act: -0.0000

Data Index: 828422 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8384. Min Act: 0.0000

Data Index: 1139314 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.7850. Min Act: -0.0000

Data Index: 508218 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8217. Min Act: -0.0000

Data Index: 168851 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1440533 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.7981. Min Act: -0.0000

Data Index: 422120 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.8490. Min Act: -0.0000

Data Index: 58398 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.4067. Min Range: -1.4067

Max Act: 0.7910. Min Act: -0.0000

Data Index: 776458 (C4 (Web Text))

Max Activating Token Index: 429