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

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

Neuron 3948 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: 0.8251. Min Range: -0.8251

Max Act: 0.7899. Min Act: -0.0000

Data Index: 351016 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7585. Min Act: -0.0000

Data Index: 891305 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.8133. Min Act: -0.0000

Data Index: 696591 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1028888 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7982. Min Act: -0.0000

Data Index: 318087 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7669. Min Act: -0.0000

Data Index: 493052 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7223. Min Act: -0.0000

Data Index: 620857 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7406. Min Act: -0.0000

Data Index: 8486 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7565. Min Act: -0.0000

Data Index: 352474 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.8251. Min Act: -0.0000

Data Index: 192991 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1234876 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1219341 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7425. Min Act: -0.0000

Data Index: 404818 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7126. Min Act: -0.0000

Data Index: 251097 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1275386 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.7010. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6590. Min Act: -0.0000

Data Index: 232143 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1310264 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1053993 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.8251. Min Range: -0.8251

Max Act: 0.6582. Min Act: -0.0000

Data Index: 294355 (C4 (Web Text))

Max Activating Token Index: 368