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

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

Neuron 644 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: 0.9708. Min Range: -0.9708

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1232874 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1123318 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7267. Min Act: -0.0000

Data Index: 447886 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1024276 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6818. Min Act: 0.0001

Data Index: 570868 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6356. Min Act: -0.0000

Data Index: 206285 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6138. Min Act: -0.0000

Data Index: 822197 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6131. Min Act: 0.0000

Data Index: 202648 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5688. Min Act: -0.0000

Data Index: 30222 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.6168. Min Act: -0.0000

Data Index: 46667 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5962. Min Act: -0.0000

Data Index: 442570 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5650. Min Act: 0.0000

Data Index: 584399 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5623. Min Act: 0.0000

Data Index: 1154412 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5567. Min Act: -0.0000

Data Index: 505461 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.5007. Min Act: -0.0000

Data Index: 8868 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.4968. Min Act: -0.0000

Data Index: 676250 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.4762. Min Act: -0.0000

Data Index: 454573 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.4869. Min Act: 0.0001

Data Index: 1208723 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.4428. Min Act: -0.0000

Data Index: 725163 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.4440. Min Act: -0.0000

Data Index: 458235 (C4 (Web Text))

Max Activating Token Index: 419