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

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

Neuron 2197 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1320677 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1010. Min Act: -0.0002

Data Index: 88316 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1046. Min Act: -0.0002

Data Index: 161832 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0992. Min Act: -0.0001

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0960. Min Act: -0.0002

Data Index: 515552 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0946. Min Act: -0.0002

Data Index: 577795 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0942. Min Act: -0.0002

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0931. Min Act: -0.0002

Data Index: 676183 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0894. Min Act: -0.0002

Data Index: 860180 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0909. Min Act: -0.0002

Data Index: 660034 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0846. Min Act: -0.0002

Data Index: 413824 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1036514 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0846. Min Act: -0.0002

Data Index: 471088 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0869. Min Act: -0.0002

Data Index: 892157 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1174917 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0824. Min Act: -0.0002

Data Index: 850599 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0821. Min Act: -0.0002

Data Index: 422188 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0849. Min Act: -0.0002

Data Index: 121745 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0814. Min Act: -0.0002

Data Index: 546300 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0816. Min Act: -0.0002

Data Index: 470393 (C4 (Web Text))

Max Activating Token Index: 257