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

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

Neuron 6065 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: 1.1228. Min Range: -1.1228

Max Act: 1.1228. Min Act: -0.0000

Data Index: 312782 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0856. Min Act: -0.0000

Data Index: 41605 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0334. Min Act: -0.0001

Data Index: 50140 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1073449 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9735. Min Act: -0.0001

Data Index: 1348013 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8271. Min Act: -0.0001

Data Index: 1143932 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8779. Min Act: -0.0001

Data Index: 440678 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1001543 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7811. Min Act: -0.0001

Data Index: 265911 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7445. Min Act: -0.0000

Data Index: 60927 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7380. Min Act: -0.0001

Data Index: 1089013 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8389. Min Act: -0.0001

Data Index: 545661 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.6959. Min Act: -0.0001

Data Index: 909441 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7036. Min Act: -0.0001

Data Index: 1009946 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1003554 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1003930 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.6779. Min Act: -0.0001

Data Index: 1028512 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7025. Min Act: -0.0001

Data Index: 469371 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7113. Min Act: -0.0000

Data Index: 764873 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.7715. Min Act: -0.0001

Data Index: 641240 (C4 (Web Text))

Max Activating Token Index: 278