Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2452 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4318. Min Range: -3.4318

Max Act: 3.4318. Min Act: -0.0000

Data Index: 169770 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.8678. Min Act: -0.0000

Data Index: 630677 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6202. Min Act: -0.0000

Data Index: 294268 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.3264. Min Act: -0.0000

Data Index: 258567 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.2763. Min Act: -0.0000

Data Index: 795638 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.2193. Min Act: -0.0000

Data Index: 551166 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.1988. Min Act: -0.0000

Data Index: 738691 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.1829. Min Act: -0.0000

Data Index: 623426 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.1277. Min Act: -0.0000

Data Index: 70806 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.1217. Min Act: -0.0000

Data Index: 610702 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.0890. Min Act: -0.0000

Data Index: 447517 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1236424 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.0053. Min Act: -0.0000

Data Index: 176785 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.9733. Min Act: -0.0000

Data Index: 396314 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.0726. Min Act: -0.0000

Data Index: 327908 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.7192. Min Act: -0.0000

Data Index: 334357 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.7852. Min Act: -0.0000

Data Index: 962064 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.7523. Min Act: -0.0000

Data Index: 190117 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.8462. Min Act: -0.0000

Data Index: 1187963 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.4318. Min Range: -3.4318

Max Act: 1.8171. Min Act: -0.0000

Data Index: 1085664 (C4 (Web Text))

Max Activating Token Index: 448