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

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

Neuron 2045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.9283. Min Act: -0.0001

Data Index: 698260 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.9113. Min Act: -0.0001

Data Index: 272316 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.8425. Min Act: -0.0001

Data Index: 137912 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1208503 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7540. Min Act: -0.0001

Data Index: 677278 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6954. Min Act: -0.0001

Data Index: 489703 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6736. Min Act: -0.0001

Data Index: 733236 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6526. Min Act: -0.0001

Data Index: 760867 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6369. Min Act: -0.0001

Data Index: 55064 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6325. Min Act: -0.0001

Data Index: 728606 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6097. Min Act: -0.0001

Data Index: 417263 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5719. Min Act: -0.0001

Data Index: 712754 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5877. Min Act: -0.0001

Data Index: 246454 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6029. Min Act: -0.0001

Data Index: 339500 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6415. Min Act: -0.0001

Data Index: 411611 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5997. Min Act: -0.0001

Data Index: 316338 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5931. Min Act: -0.0001

Data Index: 596779 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5880. Min Act: -0.0001

Data Index: 144563 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6054. Min Act: -0.0001

Data Index: 541039 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6359. Min Act: -0.0001

Data Index: 432355 (C4 (Web Text))

Max Activating Token Index: 600