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

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

Neuron 102 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0000

Data Index: 436010 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1305. Min Act: -0.0000

Data Index: 179460 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1193. Min Act: -0.0000

Data Index: 221584 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1303372 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1133. Min Act: -0.0000

Data Index: 336049 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1003. Min Act: -0.0000

Data Index: 955382 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1008. Min Act: -0.0000

Data Index: 574613 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1245042 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1007152 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0830. Min Act: -0.0000

Data Index: 782589 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1028383 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0835. Min Act: -0.0000

Data Index: 444177 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0753. Min Act: -0.0000

Data Index: 730648 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0784. Min Act: -0.0000

Data Index: 208021 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0778. Min Act: -0.0000

Data Index: 584782 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1045074 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1347455 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0728. Min Act: -0.0000

Data Index: 389963 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0716. Min Act: -0.0000

Data Index: 257891 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0737. Min Act: -0.0000

Data Index: 413559 (C4 (Web Text))

Max Activating Token Index: 322