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

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

Neuron 1545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1162848 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0976. Min Act: -0.0001

Data Index: 66625 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0908. Min Act: -0.0001

Data Index: 123241 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0932. Min Act: -0.0001

Data Index: 868399 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1178086 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1295785 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1212994 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0844. Min Act: -0.0001

Data Index: 736061 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1212210 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1306274 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1283443 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0753. Min Act: -0.0001

Data Index: 721677 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0741. Min Act: -0.0001

Data Index: 246782 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0731. Min Act: -0.0001

Data Index: 433567 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1259717 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0701. Min Act: -0.0001

Data Index: 78902 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1269657 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0722. Min Act: -0.0001

Data Index: 104432 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1085023 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0707. Min Act: -0.0001

Data Index: 95638 (C4 (Web Text))

Max Activating Token Index: 371