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

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

Neuron 1627 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: 0.8086. Min Range: -0.8086

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1125514 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.7594. Min Act: -0.0000

Data Index: 231996 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1450336 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.7115. Min Act: -0.0000

Data Index: 807731 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1076146 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6729. Min Act: -0.0000

Data Index: 568214 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6620. Min Act: -0.0000

Data Index: 689436 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6741. Min Act: -0.0000

Data Index: 789141 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1317238 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1066288 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1347039 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1567015 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1026899 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1454329 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1601585 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1652606 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6376. Min Act: -0.0000

Data Index: 872768 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1460908 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1639421 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 0.8086. Min Range: -0.8086

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1384581 (Python Code)

Max Activating Token Index: 913