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

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

Neuron 5049 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: 1.5164. Min Range: -1.5164

Max Act: 1.5164. Min Act: -0.0000

Data Index: 98831 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.4274. Min Act: -0.0000

Data Index: 315075 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3255. Min Act: -0.0000

Data Index: 101700 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.3252. Min Act: -0.0000

Data Index: 722524 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2311. Min Act: -0.0000

Data Index: 952451 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2841. Min Act: -0.0000

Data Index: 120452 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2027. Min Act: -0.0000

Data Index: 94142 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1090459 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1186050 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1213. Min Act: -0.0000

Data Index: 452321 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1437. Min Act: -0.0000

Data Index: 97766 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1457. Min Act: -0.0000

Data Index: 953781 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.2216. Min Act: -0.0000

Data Index: 790646 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1223522 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.0966. Min Act: -0.0000

Data Index: 833792 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1636. Min Act: -0.0000

Data Index: 75418 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1161538 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.1496. Min Act: -0.0000

Data Index: 4965 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.0925. Min Act: -0.0000

Data Index: 401772 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.5164. Min Range: -1.5164

Max Act: 1.0625. Min Act: -0.0000

Data Index: 972206 (C4 (Web Text))

Max Activating Token Index: 147