Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0002

Data Index: 901761 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0936. Min Act: -0.0002

Data Index: 78097 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0922. Min Act: -0.0002

Data Index: 990928 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1251817 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0850. Min Act: -0.0002

Data Index: 111163 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1196276 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1226190 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0871. Min Act: -0.0002

Data Index: 863346 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0909. Min Act: -0.0002

Data Index: 354534 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0882. Min Act: -0.0002

Data Index: 102099 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1029533 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0806. Min Act: -0.0002

Data Index: 938536 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0838. Min Act: -0.0002

Data Index: 493730 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0832. Min Act: -0.0002

Data Index: 238681 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1157834 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0851. Min Act: -0.0002

Data Index: 66025 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0832. Min Act: -0.0002

Data Index: 535224 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0820. Min Act: -0.0002

Data Index: 485275 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0809. Min Act: -0.0002

Data Index: 51290 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0855. Min Act: -0.0002

Data Index: 615373 (C4 (Web Text))

Max Activating Token Index: 282