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

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

Neuron 1438 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: 9.2030. Min Range: -9.2030

Max Act: 9.2030. Min Act: -0.0000

Data Index: 630996 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.8970. Min Act: -0.0000

Data Index: 1125280 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.9951. Min Act: -0.0000

Data Index: 1316266 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.4989. Min Act: -0.0000

Data Index: 1260738 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.4047. Min Act: -0.0000

Data Index: 306166 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.0433. Min Act: -0.0000

Data Index: 30266 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.3451. Min Act: -0.0000

Data Index: 1034374 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.1086. Min Act: -0.0000

Data Index: 1622909 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.0692. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.9990. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.8696. Min Act: -0.0000

Data Index: 51521 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.0248. Min Act: -0.0000

Data Index: 616226 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.0412. Min Act: -0.0000

Data Index: 1062958 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.4913. Min Act: -0.0000

Data Index: 953062 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.3810. Min Act: -0.0000

Data Index: 529936 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 9.2030. Min Range: -9.2030

Max Act: 8.0166. Min Act: -0.0000

Data Index: 940341 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.6419. Min Act: -0.0000

Data Index: 213473 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.4328. Min Act: -0.0000

Data Index: 1431143 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.1644. Min Act: -0.0000

Data Index: 1275770 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 9.2030. Min Range: -9.2030

Max Act: 7.7554. Min Act: -0.0000

Data Index: 463389 (C4 (Web Text))

Max Activating Token Index: 693