Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.8089. Min Act: -0.0001

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.8067. Min Act: -0.0000

Data Index: 368953 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7378. Min Act: -0.0001

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6277. Min Act: -0.0001

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7260. Min Act: -0.0000

Data Index: 234738 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6036. Min Act: -0.0001

Data Index: 790244 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6426. Min Act: -0.0001

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1322402 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6422. Min Act: -0.0001

Data Index: 467365 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6825. Min Act: -0.0001

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7246. Min Act: -0.0001

Data Index: 107857 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6829. Min Act: -0.0001

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6029. Min Act: -0.0001

Data Index: 99268 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6434. Min Act: -0.0001

Data Index: 299748 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6252. Min Act: -0.0001

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6604. Min Act: -0.0001

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6088. Min Act: -0.0001

Data Index: 413099 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5828. Min Act: -0.0001

Data Index: 797525 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6215. Min Act: -0.0001

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6237. Min Act: -0.0001

Data Index: 514072 (C4 (Web Text))

Max Activating Token Index: 481