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

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

Neuron 3855 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: 0.9204. Min Range: -0.9204

Max Act: 0.9204. Min Act: -0.0001

Data Index: 190182 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8724. Min Act: -0.0001

Data Index: 713035 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1171557 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7688. Min Act: -0.0001

Data Index: 269805 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7848. Min Act: -0.0001

Data Index: 704306 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7454. Min Act: -0.0001

Data Index: 875946 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7342. Min Act: -0.0001

Data Index: 416433 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6802. Min Act: -0.0001

Data Index: 915611 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7090. Min Act: -0.0001

Data Index: 1184729 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1283687 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7471. Min Act: -0.0001

Data Index: 629855 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6820. Min Act: -0.0001

Data Index: 978876 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6963. Min Act: -0.0001

Data Index: 434567 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7032. Min Act: -0.0001

Data Index: 586564 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6598. Min Act: -0.0001

Data Index: 10460 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7025. Min Act: -0.0001

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6730. Min Act: -0.0001

Data Index: 615144 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6525. Min Act: -0.0001

Data Index: 525748 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6559. Min Act: -0.0001

Data Index: 29358 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6537. Min Act: -0.0001

Data Index: 668463 (C4 (Web Text))

Max Activating Token Index: 372