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

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

Neuron 3059 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.9513. Min Act: 0.0001

Data Index: 746845 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.9633. Min Act: -0.0000

Data Index: 104825 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.3348. Min Act: -0.0000

Data Index: 646007 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.2061. Min Act: 0.0000

Data Index: 1300067 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.1965. Min Act: 0.0000

Data Index: 1226525 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.9633. Min Range: -1.9633

Max Act: 1.0844. Min Act: 0.0000

Data Index: 338367 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.9209. Min Act: -0.0000

Data Index: 667081 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.9484. Min Act: -0.0000

Data Index: 405988 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8711. Min Act: 0.0000

Data Index: 649708 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.9230. Min Act: 0.0000

Data Index: 750464 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8584. Min Act: 0.0000

Data Index: 1238531 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8232. Min Act: 0.0000

Data Index: 336025 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1342585 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8299. Min Act: 0.0000

Data Index: 796694 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8047. Min Act: -0.0000

Data Index: 120200 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8096. Min Act: -0.0000

Data Index: 250383 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.8080. Min Act: -0.0000

Data Index: 864280 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1356342 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1134186 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.9633. Min Range: -1.9633

Max Act: 0.7737. Min Act: -0.0000

Data Index: 932869 (C4 (Web Text))

Max Activating Token Index: 876