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

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

Neuron 2715 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.9024. Min Act: -0.0000

Data Index: 615642 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7494. Min Act: -0.0000

Data Index: 393947 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1170103 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6297. Min Act: 0.0000

Data Index: 659344 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1283632 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6386. Min Act: -0.0000

Data Index: 404441 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5811. Min Act: -0.0000

Data Index: 458703 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1151433 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5684. Min Act: 0.0000

Data Index: 357950 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5302. Min Act: -0.0000

Data Index: 991871 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1033765 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5453. Min Act: -0.0000

Data Index: 860859 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5627. Min Act: -0.0000

Data Index: 831722 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5422. Min Act: 0.0000

Data Index: 510773 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5399. Min Act: -0.0000

Data Index: 773115 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5175. Min Act: -0.0000

Data Index: 491125 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5327. Min Act: -0.0000

Data Index: 622485 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1217636 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5208. Min Act: 0.0000

Data Index: 945831 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5076. Min Act: 0.0001

Data Index: 672448 (C4 (Web Text))

Max Activating Token Index: 713