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

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

Neuron 1444 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1101515 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.2526. Min Act: -0.0000

Data Index: 543164 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.0842. Min Act: 0.0000

Data Index: 866478 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.0725. Min Act: -0.0000

Data Index: 322098 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.0470. Min Act: -0.0000

Data Index: 451411 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.1017. Min Act: -0.0000

Data Index: 172856 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.0597. Min Act: -0.0000

Data Index: 457763 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.2526. Min Range: -1.2526

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1015252 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9906. Min Act: -0.0000

Data Index: 42925 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9288. Min Act: -0.0000

Data Index: 507950 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1122873 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9570. Min Act: -0.0000

Data Index: 307015 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9559. Min Act: -0.0000

Data Index: 154461 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9329. Min Act: -0.0000

Data Index: 785629 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9271. Min Act: -0.0000

Data Index: 945629 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.8580. Min Act: -0.0000

Data Index: 106437 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.8580. Min Act: -0.0000

Data Index: 908404 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.8820. Min Act: -0.0000

Data Index: 87356 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9094. Min Act: -0.0000

Data Index: 535099 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.2526. Min Range: -1.2526

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1313632 (C4 (Web Text))

Max Activating Token Index: 30