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

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

Neuron 5250 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: 2.4873. Min Range: -2.4873

Max Act: 2.4873. Min Act: -0.0000

Data Index: 588481 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.0532. Min Act: -0.0000

Data Index: 1073552 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.8646. Min Act: -0.0000

Data Index: 500500 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.6913. Min Act: -0.0000

Data Index: 627093 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.6659. Min Act: -0.0000

Data Index: 884713 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.4970. Min Act: -0.0000

Data Index: 70779 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.3251. Min Act: -0.0000

Data Index: 948648 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.3750. Min Act: -0.0000

Data Index: 150830 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.4164. Min Act: -0.0000

Data Index: 523788 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.3238. Min Act: -0.0000

Data Index: 667661 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1286314 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.2874. Min Act: -0.0000

Data Index: 232307 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.2823. Min Act: -0.0000

Data Index: 285842 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.2371. Min Act: -0.0000

Data Index: 372636 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.2150. Min Act: -0.0000

Data Index: 652585 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.1956. Min Act: -0.0000

Data Index: 413359 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.1326. Min Act: -0.0000

Data Index: 254748 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.1582. Min Act: -0.0000

Data Index: 579642 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1088893 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1225881 (C4 (Web Text))

Max Activating Token Index: 336