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

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

Neuron 4646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4238. Min Range: -2.4238

Max Act: 2.4238. Min Act: -0.0000

Data Index: 1007870 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 2.4238. Min Range: -2.4238

Max Act: 2.2124. Min Act: -0.0000

Data Index: 195820 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.8061. Min Act: -0.0000

Data Index: 312449 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.7153. Min Act: -0.0000

Data Index: 173734 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.8629. Min Act: -0.0000

Data Index: 686707 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.6251. Min Act: -0.0000

Data Index: 355780 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1197449 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.4238. Min Range: -2.4238

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1313947 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.5995. Min Act: -0.0000

Data Index: 149569 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.3601. Min Act: -0.0000

Data Index: 1089603 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1034104 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.6124. Min Act: -0.0000

Data Index: 733067 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4778. Min Act: -0.0000

Data Index: 596558 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.7409. Min Act: -0.0000

Data Index: 531133 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1028947 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1488923 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4499. Min Act: -0.0000

Data Index: 102433 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4417. Min Act: -0.0000

Data Index: 870509 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.4000. Min Act: -0.0000

Data Index: 540197 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.4238. Min Range: -2.4238

Max Act: 1.3017. Min Act: -0.0000

Data Index: 778940 (C4 (Web Text))

Max Activating Token Index: 783