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

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

Neuron 35 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.1213. Min Act: -0.0001

Data Index: 252666 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9000. Min Act: -0.0001

Data Index: 1098980 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9071. Min Act: -0.0001

Data Index: 995446 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8701. Min Act: -0.0001

Data Index: 619332 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7372. Min Act: -0.0001

Data Index: 105402 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9022. Min Act: -0.0001

Data Index: 461962 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1133254 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7430. Min Act: -0.0001

Data Index: 995869 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.6576. Min Act: -0.0001

Data Index: 449473 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7118. Min Act: -0.0001

Data Index: 326143 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1202511 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1615601 (Python Code)

Max Activating Token Index: 341

Text #12

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.6232. Min Act: -0.0001

Data Index: 999785 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5876. Min Act: -0.0001

Data Index: 1012342 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5845. Min Act: -0.0001

Data Index: 988465 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5883. Min Act: -0.0001

Data Index: 947567 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.6052. Min Act: -0.0001

Data Index: 298922 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5507. Min Act: -0.0001

Data Index: 178202 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.4902. Min Act: -0.0001

Data Index: 743790 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.5677. Min Act: -0.0001

Data Index: 359884 (C4 (Web Text))

Max Activating Token Index: 950