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

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

Neuron 5491 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1203333 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.3485. Min Act: -0.0000

Data Index: 995773 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.1039. Min Act: -0.0000

Data Index: 601648 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0128. Min Act: -0.0000

Data Index: 181121 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0385. Min Act: -0.0000

Data Index: 399790 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9652. Min Act: -0.0000

Data Index: 494534 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9624. Min Act: -0.0000

Data Index: 618532 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.3485. Min Range: -1.3485

Max Act: 1.0758. Min Act: -0.0000

Data Index: 82579 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9480. Min Act: -0.0000

Data Index: 74559 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9534. Min Act: -0.0000

Data Index: 259515 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8457. Min Act: -0.0000

Data Index: 114324 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8997. Min Act: -0.0000

Data Index: 449237 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8801. Min Act: -0.0000

Data Index: 479388 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8983. Min Act: -0.0000

Data Index: 325751 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8982. Min Act: -0.0000

Data Index: 22435 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8378. Min Act: -0.0000

Data Index: 195427 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1254938 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1076799 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8320. Min Act: -0.0000

Data Index: 702208 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.3485. Min Range: -1.3485

Max Act: 0.8886. Min Act: -0.0000

Data Index: 28277 (C4 (Web Text))

Max Activating Token Index: 704