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

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

Neuron 744 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.5150. Min Act: -0.0000

Data Index: 282896 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2560. Min Act: -0.0000

Data Index: 885679 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2806. Min Act: -0.0000

Data Index: 380491 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1282978 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1182932 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2404. Min Act: -0.0000

Data Index: 516624 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2297. Min Act: -0.0000

Data Index: 993942 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2306. Min Act: -0.0001

Data Index: 402478 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1310165 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2233. Min Act: -0.0000

Data Index: 818573 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2144. Min Act: -0.0000

Data Index: 941331 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1118919 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2158. Min Act: -0.0000

Data Index: 346101 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.1902. Min Act: -0.0000

Data Index: 831043 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1196671 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2045. Min Act: -0.0000

Data Index: 617996 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2102. Min Act: -0.0000

Data Index: 332513 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2038. Min Act: -0.0001

Data Index: 797798 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.1957. Min Act: -0.0001

Data Index: 180454 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2012. Min Act: -0.0001

Data Index: 266050 (C4 (Web Text))

Max Activating Token Index: 252