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

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

Neuron 5116 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 754326 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1145. Min Act: -0.0001

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1177. Min Act: -0.0001

Data Index: 441162 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1185580 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1298113 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1259621 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1047. Min Act: -0.0001

Data Index: 975348 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0989. Min Act: -0.0001

Data Index: 738869 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0907. Min Act: -0.0001

Data Index: 213258 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0959. Min Act: -0.0001

Data Index: 392038 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1369144 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0876. Min Act: -0.0001

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1017529 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0912. Min Act: -0.0001

Data Index: 110303 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0892. Min Act: -0.0001

Data Index: 117990 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1015620 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1335119 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1440947 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1061276 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.0853. Min Act: -0.0001

Data Index: 666978 (C4 (Web Text))

Max Activating Token Index: 382