Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 797413 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0517. Min Act: -0.0002

Data Index: 921480 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0503. Min Act: -0.0002

Data Index: 835331 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0509. Min Act: -0.0002

Data Index: 127867 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0505. Min Act: -0.0002

Data Index: 27536 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0429. Min Act: -0.0002

Data Index: 523155 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1050591 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0405. Min Act: -0.0003

Data Index: 115586 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0388. Min Act: -0.0003

Data Index: 381473 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0411. Min Act: -0.0003

Data Index: 143673 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1063312 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1139067 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0376. Min Act: -0.0002

Data Index: 615374 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0375. Min Act: -0.0004

Data Index: 791878 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0381. Min Act: -0.0003

Data Index: 609650 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0382. Min Act: -0.0003

Data Index: 181415 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0379. Min Act: -0.0002

Data Index: 222275 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0374. Min Act: -0.0002

Data Index: 906232 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0374. Min Act: -0.0003

Data Index: 603835 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0389. Min Act: -0.0003

Data Index: 356691 (C4 (Web Text))

Max Activating Token Index: 725