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

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

Neuron 912 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: 0.9159. Min Range: -0.9159

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1019048 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1122958 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9054. Min Act: -0.0000

Data Index: 953749 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8664. Min Act: -0.0000

Data Index: 992293 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9159. Min Act: -0.0000

Data Index: 816049 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1224011 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1296281 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.9059. Min Act: -0.0000

Data Index: 992622 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8853. Min Act: -0.0000

Data Index: 313685 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8188. Min Act: -0.0000

Data Index: 333229 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1323621 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8312. Min Act: -0.0000

Data Index: 304136 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1186520 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8295. Min Act: -0.0000

Data Index: 896562 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8429. Min Act: -0.0000

Data Index: 391972 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.7966. Min Act: -0.0000

Data Index: 12989 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.7926. Min Act: -0.0000

Data Index: 774199 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8524. Min Act: -0.0000

Data Index: 602203 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8063. Min Act: -0.0000

Data Index: 761732 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.9159. Min Range: -0.9159

Max Act: 0.8033. Min Act: -0.0000

Data Index: 523123 (C4 (Web Text))

Max Activating Token Index: 119