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

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

Neuron 2376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1254890 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1601. Min Act: -0.0001

Data Index: 529398 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1594. Min Act: -0.0001

Data Index: 984996 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1554. Min Act: -0.0001

Data Index: 62486 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1143023 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1041642 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1237. Min Act: -0.0001

Data Index: 333898 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1322. Min Act: -0.0001

Data Index: 814539 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1251. Min Act: -0.0001

Data Index: 116173 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1337. Min Act: -0.0001

Data Index: 269599 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1232. Min Act: -0.0001

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1249. Min Act: -0.0001

Data Index: 363932 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1194. Min Act: -0.0001

Data Index: 733584 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1244. Min Act: -0.0001

Data Index: 115442 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1073554 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1111. Min Act: -0.0001

Data Index: 9447 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1102. Min Act: -0.0001

Data Index: 169243 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1182. Min Act: -0.0001

Data Index: 228402 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1126. Min Act: -0.0001

Data Index: 158885 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1189519 (C4 (Web Text))

Max Activating Token Index: 973