Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1373606 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1563591 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1571183 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1599004 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1466916 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1519188 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1473609 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1535351 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1595902 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1384126 (Python Code)

Max Activating Token Index: 916

Text #10

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1527175 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1583777 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1490178 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1585635 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1390065 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1363618 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1594713 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1518889 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1395775 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1596923 (Python Code)

Max Activating Token Index: 589