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

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

Neuron 3162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.1710. Min Act: -0.0000

Data Index: 937918 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.1257. Min Act: -0.0000

Data Index: 30254 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.1268. Min Act: -0.0000

Data Index: 987264 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.1315. Min Act: -0.0000

Data Index: 729440 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0607. Min Act: -0.0000

Data Index: 458556 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0405. Min Act: -0.0000

Data Index: 531269 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1224314 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9368. Min Act: -0.0000

Data Index: 642639 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.1710. Min Range: -1.1710

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1043259 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1147565 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1274208 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8522. Min Act: -0.0000

Data Index: 15946 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1196670 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1004524 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8980. Min Act: -0.0000

Data Index: 446827 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1203480 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8843. Min Act: -0.0000

Data Index: 182294 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8769. Min Act: -0.0000

Data Index: 302866 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.8144. Min Act: -0.0000

Data Index: 615947 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.1710. Min Range: -1.1710

Max Act: 0.9244. Min Act: -0.0000

Data Index: 218102 (C4 (Web Text))

Max Activating Token Index: 471