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

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

Neuron 3010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1275743 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.0758. Min Act: -0.0000

Data Index: 280205 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.0721. Min Act: -0.0000

Data Index: 824849 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.0434. Min Act: -0.0000

Data Index: 75969 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9866. Min Act: -0.0000

Data Index: 368308 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8717. Min Act: -0.0000

Data Index: 750708 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.0057. Min Act: -0.0000

Data Index: 238109 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9032. Min Act: -0.0000

Data Index: 242791 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9305. Min Act: -0.0000

Data Index: 960618 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9413. Min Act: -0.0000

Data Index: 807211 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1320440 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9215. Min Act: -0.0000

Data Index: 507290 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8041. Min Act: -0.0000

Data Index: 779516 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8769. Min Act: -0.0000

Data Index: 357455 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8215. Min Act: -0.0000

Data Index: 110607 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8869. Min Act: -0.0000

Data Index: 528251 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8354. Min Act: -0.0000

Data Index: 330611 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7940. Min Act: -0.0000

Data Index: 891898 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1219842 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7941. Min Act: -0.0000

Data Index: 464133 (C4 (Web Text))

Max Activating Token Index: 22