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

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

Neuron 1707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0057. Min Range: -2.0057

Max Act: 2.0057. Min Act: -0.0000

Data Index: 171468 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.9149. Min Act: -0.0000

Data Index: 462254 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.7838. Min Act: -0.0000

Data Index: 176430 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.7579. Min Act: -0.0000

Data Index: 208438 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6511. Min Act: -0.0001

Data Index: 412681 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4470. Min Act: -0.0000

Data Index: 265219 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1346644 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.6455. Min Act: -0.0000

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1018654 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5511. Min Act: -0.0000

Data Index: 695558 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4256. Min Act: -0.0000

Data Index: 690473 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.5766. Min Act: -0.0000

Data Index: 757002 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.3447. Min Act: -0.0000

Data Index: 530406 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1109814 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.3240. Min Act: -0.0000

Data Index: 774011 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4028. Min Act: -0.0000

Data Index: 392225 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1077676 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.2714. Min Act: -0.0000

Data Index: 51573 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.4314. Min Act: -0.0000

Data Index: 1218730 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.0057. Min Range: -2.0057

Max Act: 1.3902. Min Act: -0.0000

Data Index: 340942 (C4 (Web Text))

Max Activating Token Index: 309