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

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

Neuron 2096 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.5737. Min Act: -0.0001

Data Index: 962093 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4826. Min Act: -0.0001

Data Index: 1328327 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.5751. Min Act: -0.0001

Data Index: 1314715 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.5176. Min Act: -0.0001

Data Index: 1204582 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4331. Min Act: -0.0001

Data Index: 735274 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4087. Min Act: -0.0001

Data Index: 1316439 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.3313. Min Act: -0.0001

Data Index: 296125 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4389. Min Act: -0.0001

Data Index: 832325 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2684. Min Act: -0.0001

Data Index: 606168 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.3471. Min Act: -0.0001

Data Index: 534302 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4113. Min Act: -0.0001

Data Index: 113310 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.4539. Min Act: -0.0001

Data Index: 1082975 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2299. Min Act: -0.0001

Data Index: 3587 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2779. Min Act: -0.0001

Data Index: 213873 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2294. Min Act: -0.0001

Data Index: 1120304 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2183. Min Act: -0.0001

Data Index: 954960 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2505. Min Act: -0.0001

Data Index: 479513 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2541. Min Act: -0.0001

Data Index: 1250824 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2201. Min Act: -0.0001

Data Index: 1211315 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2217. Min Act: -0.0001

Data Index: 548956 (C4 (Web Text))

Max Activating Token Index: 792