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

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

Neuron 2653 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: 0.3258. Min Range: -0.3258

Max Act: 0.3258. Min Act: -0.0000

Data Index: 947722 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3052. Min Act: -0.0000

Data Index: 416702 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3109. Min Act: -0.0000

Data Index: 871453 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1233530 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2835. Min Act: -0.0000

Data Index: 739329 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2907. Min Act: -0.0000

Data Index: 73685 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2818. Min Act: -0.0000

Data Index: 206741 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2718. Min Act: -0.0000

Data Index: 713231 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1099994 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2505. Min Act: -0.0000

Data Index: 369738 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2370. Min Act: -0.0000

Data Index: 835249 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1249807 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1136383 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1120348 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2327. Min Act: -0.0000

Data Index: 579662 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2219. Min Act: -0.0000

Data Index: 371237 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2294. Min Act: -0.0000

Data Index: 670326 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2160. Min Act: -0.0000

Data Index: 844445 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2218. Min Act: 0.0000

Data Index: 1345277 (C4 (Web Text))

Max Activating Token Index: 527