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

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

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0517. Min Act: -0.0001

Data Index: 388895 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1228270 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9369. Min Act: -0.0001

Data Index: 563468 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9407. Min Act: -0.0000

Data Index: 901263 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8667. Min Act: -0.0001

Data Index: 667070 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8650. Min Act: -0.0001

Data Index: 573821 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1295494 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9097. Min Act: -0.0001

Data Index: 493264 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8476. Min Act: -0.0001

Data Index: 753002 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8789. Min Act: -0.0001

Data Index: 938326 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8939. Min Act: -0.0001

Data Index: 564102 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8741. Min Act: -0.0001

Data Index: 195762 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8147. Min Act: -0.0001

Data Index: 90437 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1167974 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8578. Min Act: -0.0001

Data Index: 1339342 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1174137 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8210. Min Act: -0.0001

Data Index: 870232 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8473. Min Act: -0.0001

Data Index: 230427 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1252519 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1002926 (C4 (Web Text))

Max Activating Token Index: 184