Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3753 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.9135. Min Act: -0.0001

Data Index: 1203917 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.9506. Min Act: -0.0001

Data Index: 815498 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.8625. Min Act: -0.0001

Data Index: 719146 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7855. Min Act: -0.0001

Data Index: 1271522 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7938. Min Act: -0.0001

Data Index: 117990 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6844. Min Act: -0.0001

Data Index: 854830 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7676. Min Act: -0.0001

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7306. Min Act: -0.0001

Data Index: 1088747 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7110. Min Act: -0.0001

Data Index: 311501 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6578. Min Act: -0.0001

Data Index: 441162 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1557721 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6535. Min Act: -0.0001

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6896. Min Act: -0.0001

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7085. Min Act: -0.0001

Data Index: 508050 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.7063. Min Act: -0.0001

Data Index: 1297473 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1341694 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6715. Min Act: -0.0001

Data Index: 76547 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6650. Min Act: -0.0001

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.9506. Min Range: -0.9506

Max Act: 0.6459. Min Act: -0.0001

Data Index: 223060 (C4 (Web Text))

Max Activating Token Index: 178