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

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

Neuron 4989 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: 1.4072. Min Range: -1.4072

Max Act: 1.3277. Min Act: -0.0000

Data Index: 662156 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.4072. Min Act: 0.0000

Data Index: 1235537 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.2584. Min Act: -0.0000

Data Index: 143211 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.3053. Min Act: -0.0000

Data Index: 840920 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.2809. Min Act: -0.0000

Data Index: 187047 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.1265. Min Act: -0.0000

Data Index: 233886 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.1153. Min Act: -0.0000

Data Index: 738684 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.1697. Min Act: -0.0000

Data Index: 908646 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0998. Min Act: -0.0000

Data Index: 1071316 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0154. Min Act: -0.0000

Data Index: 863880 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1137682 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0733. Min Act: -0.0000

Data Index: 528865 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0659. Min Act: -0.0000

Data Index: 582795 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1355484 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.4072. Min Range: -1.4072

Max Act: 1.0004. Min Act: -0.0000

Data Index: 184330 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.4072. Min Range: -1.4072

Max Act: 0.9713. Min Act: -0.0000

Data Index: 349020 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.4072. Min Range: -1.4072

Max Act: 0.9717. Min Act: -0.0000

Data Index: 777401 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.4072. Min Range: -1.4072

Max Act: 0.9677. Min Act: -0.0000

Data Index: 570309 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.4072. Min Range: -1.4072

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1161377 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.4072. Min Range: -1.4072

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1185242 (C4 (Web Text))

Max Activating Token Index: 815