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

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

Neuron 239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1338596 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1065419 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4607. Min Act: -0.0000

Data Index: 656915 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4504. Min Act: -0.0000

Data Index: 527136 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4281. Min Act: -0.0000

Data Index: 911892 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4163. Min Act: -0.0000

Data Index: 635532 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4241. Min Act: -0.0000

Data Index: 3596 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4232. Min Act: -0.0000

Data Index: 110267 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4287. Min Act: -0.0000

Data Index: 494978 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4168. Min Act: -0.0000

Data Index: 918843 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1157688 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4065. Min Act: -0.0000

Data Index: 812690 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1183434 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3893. Min Act: -0.0000

Data Index: 855527 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1218804 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3987. Min Act: -0.0000

Data Index: 76403 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3823. Min Act: -0.0000

Data Index: 969444 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1173463 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3905. Min Act: -0.0000

Data Index: 855060 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3788. Min Act: -0.0000

Data Index: 325218 (C4 (Web Text))

Max Activating Token Index: 913