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

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

Neuron 344 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: 1.4078. Min Range: -1.4078

Max Act: 1.4078. Min Act: -0.0000

Data Index: 679443 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.2010. Min Act: -0.0000

Data Index: 175264 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0736. Min Act: -0.0000

Data Index: 495844 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9571. Min Act: -0.0000

Data Index: 670103 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0514. Min Act: -0.0000

Data Index: 690601 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9300. Min Act: -0.0000

Data Index: 346597 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9270. Min Act: -0.0000

Data Index: 169332 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9089. Min Act: -0.0000

Data Index: 261791 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8616. Min Act: -0.0000

Data Index: 637399 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9152. Min Act: -0.0000

Data Index: 216462 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9014. Min Act: -0.0000

Data Index: 584529 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1207090 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8901. Min Act: -0.0000

Data Index: 439974 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8241. Min Act: -0.0000

Data Index: 412680 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1043453 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8428. Min Act: -0.0000

Data Index: 31196 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8281. Min Act: -0.0000

Data Index: 331287 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8285. Min Act: -0.0000

Data Index: 857784 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.8226. Min Act: -0.0000

Data Index: 129333 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1088419 (C4 (Web Text))

Max Activating Token Index: 406