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

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

Neuron 3656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2308. Min Range: -2.2308

Max Act: 2.2308. Min Act: -0.0000

Data Index: 169982 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 2.2308. Min Range: -2.2308

Max Act: 2.0098. Min Act: -0.0000

Data Index: 760152 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.5643. Min Act: -0.0000

Data Index: 863299 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.4321. Min Act: -0.0000

Data Index: 178209 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1057851 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3517. Min Act: -0.0000

Data Index: 666806 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3363. Min Act: -0.0000

Data Index: 349614 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.2934. Min Act: -0.0000

Data Index: 586461 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1062594 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3083. Min Act: -0.0000

Data Index: 26500 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.2763. Min Act: -0.0000

Data Index: 842769 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3151. Min Act: -0.0000

Data Index: 163799 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3053. Min Act: -0.0000

Data Index: 159508 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.3411. Min Act: -0.0000

Data Index: 166405 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.2783. Min Act: -0.0000

Data Index: 335690 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.1321. Min Act: -0.0000

Data Index: 44736 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1265952 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.1439. Min Act: -0.0000

Data Index: 965548 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.1580. Min Act: -0.0000

Data Index: 903241 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.2308. Min Range: -2.2308

Max Act: 1.1878. Min Act: -0.0000

Data Index: 623837 (C4 (Web Text))

Max Activating Token Index: 159