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

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

Neuron 5539 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1356. Min Range: -2.1356

Max Act: 2.1356. Min Act: -0.0000

Data Index: 1070406 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.7519. Min Act: -0.0000

Data Index: 1179488 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.8476. Min Act: -0.0000

Data Index: 448468 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1297057 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.6053. Min Act: -0.0000

Data Index: 699595 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.8095. Min Act: -0.0000

Data Index: 855855 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1251808 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1342465 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.5063. Min Act: -0.0000

Data Index: 973870 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.5972. Min Act: -0.0000

Data Index: 557204 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1120342 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4913. Min Act: -0.0000

Data Index: 873743 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4669. Min Act: -0.0000

Data Index: 193493 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4418. Min Act: -0.0000

Data Index: 103676 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1278569 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4131. Min Act: -0.0000

Data Index: 989449 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.4072. Min Act: -0.0000

Data Index: 110533 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.3981. Min Act: -0.0000

Data Index: 191891 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.3080. Min Act: -0.0000

Data Index: 158170 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 2.1356. Min Range: -2.1356

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1147309 (C4 (Web Text))

Max Activating Token Index: 795