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

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

Neuron 1981 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: 0.9439. Min Range: -0.9439

Max Act: 0.9414. Min Act: -0.0001

Data Index: 684905 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9035. Min Act: -0.0001

Data Index: 475755 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1063062 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8151. Min Act: -0.0001

Data Index: 1026588 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8362. Min Act: -0.0001

Data Index: 894685 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1056224 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7919. Min Act: -0.0001

Data Index: 262033 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8302. Min Act: -0.0001

Data Index: 212928 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7814. Min Act: -0.0001

Data Index: 1006545 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1059968 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7141. Min Act: -0.0001

Data Index: 138387 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7243. Min Act: -0.0001

Data Index: 612819 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1303706 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.6687. Min Act: -0.0001

Data Index: 623572 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7436. Min Act: -0.0001

Data Index: 688122 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7380. Min Act: -0.0001

Data Index: 273707 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7163. Min Act: -0.0001

Data Index: 696558 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1271302 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1178029 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.7018. Min Act: -0.0001

Data Index: 126854 (C4 (Web Text))

Max Activating Token Index: 932