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

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

Neuron 3237 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.5371. Min Act: -0.0000

Data Index: 1254953 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.5394. Min Act: -0.0001

Data Index: 775183 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.3951. Min Act: -0.0001

Data Index: 751205 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.3531. Min Act: -0.0001

Data Index: 134064 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1846. Min Act: -0.0000

Data Index: 446908 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2374. Min Act: -0.0000

Data Index: 961921 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1294. Min Act: -0.0000

Data Index: 938818 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1217. Min Act: -0.0001

Data Index: 442101 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1046. Min Act: -0.0001

Data Index: 666958 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2175. Min Act: -0.0001

Data Index: 992293 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1726. Min Act: -0.0000

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1265. Min Act: -0.0000

Data Index: 117522 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1053. Min Act: -0.0001

Data Index: 561687 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1318. Min Act: -0.0000

Data Index: 860646 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1241. Min Act: -0.0001

Data Index: 282215 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1531761 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0909. Min Act: -0.0000

Data Index: 478640 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0775. Min Act: -0.0001

Data Index: 559557 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1148. Min Act: -0.0001

Data Index: 1284001 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1067. Min Act: -0.0001

Data Index: 876690 (C4 (Web Text))

Max Activating Token Index: 844