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

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

Neuron 1307 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0000

Data Index: 884605 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7289. Min Act: -0.0000

Data Index: 469501 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7085. Min Act: -0.0000

Data Index: 489810 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6783. Min Act: -0.0000

Data Index: 185306 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6326. Min Act: 0.0000

Data Index: 964410 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6124. Min Act: -0.0000

Data Index: 789594 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6379. Min Act: -0.0000

Data Index: 873814 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5938. Min Act: 0.0000

Data Index: 1252824 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5927. Min Act: 0.0000

Data Index: 1111930 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6134. Min Act: 0.0000

Data Index: 624095 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5746. Min Act: -0.0000

Data Index: 525444 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1232011 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5916. Min Act: -0.0000

Data Index: 354489 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1016685 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5831. Min Act: -0.0000

Data Index: 311640 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1025447 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5481. Min Act: 0.0000

Data Index: 1117257 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5395. Min Act: -0.0000

Data Index: 753827 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5222. Min Act: -0.0000

Data Index: 766719 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5410. Min Act: -0.0000

Data Index: 598443 (C4 (Web Text))

Max Activating Token Index: 955