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

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

Neuron 5012 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0552. Min Range: -1.0552

Max Act: 1.0022. Min Act: -0.0000

Data Index: 38803 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1032761 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.0552. Min Range: -1.0552

Max Act: 1.0552. Min Act: 0.0000

Data Index: 1217599 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8640. Min Act: -0.0000

Data Index: 271821 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8147. Min Act: -0.0000

Data Index: 615606 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8015. Min Act: -0.0000

Data Index: 726600 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.8283. Min Act: -0.0000

Data Index: 53481 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1191410 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1175585 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7949. Min Act: -0.0000

Data Index: 747396 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1356696 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1246975 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7486. Min Act: -0.0000

Data Index: 317798 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7735. Min Act: -0.0000

Data Index: 444619 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1238200 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7238. Min Act: -0.0000

Data Index: 397158 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7531. Min Act: 0.0000

Data Index: 657980 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.7339. Min Act: -0.0000

Data Index: 191055 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.6926. Min Act: 0.0000

Data Index: 1183639 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.6359. Min Act: -0.0000

Data Index: 187504 (C4 (Web Text))

Max Activating Token Index: 412