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

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

Neuron 4002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.1855. Min Act: -0.0001

Data Index: 1347283 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.1451. Min Act: -0.0001

Data Index: 430728 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.0508. Min Act: -0.0001

Data Index: 231983 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.0471. Min Act: -0.0001

Data Index: 168571 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.0382. Min Act: -0.0001

Data Index: 41645 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.0316. Min Act: -0.0001

Data Index: 374184 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9796. Min Act: -0.0001

Data Index: 953417 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9659. Min Act: -0.0001

Data Index: 1213919 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9971. Min Act: -0.0001

Data Index: 1175433 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9886. Min Act: -0.0001

Data Index: 411463 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9080. Min Act: -0.0001

Data Index: 470438 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9802. Min Act: -0.0001

Data Index: 842197 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1318442 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.1855. Min Range: -1.1855

Max Act: 1.0096. Min Act: -0.0001

Data Index: 1157478 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9921. Min Act: -0.0001

Data Index: 1029147 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9292. Min Act: -0.0001

Data Index: 108445 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9270. Min Act: -0.0001

Data Index: 1173694 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9489. Min Act: -0.0001

Data Index: 659907 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9446. Min Act: -0.0001

Data Index: 849106 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.1855. Min Range: -1.1855

Max Act: 0.9382. Min Act: -0.0001

Data Index: 374506 (C4 (Web Text))

Max Activating Token Index: 93