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

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

Neuron 2047 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.6259. Min Act: 0.0000

Data Index: 187852 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3878. Min Act: -0.0000

Data Index: 766742 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3555. Min Act: -0.0000

Data Index: 834317 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1090652 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3751. Min Act: -0.0000

Data Index: 224089 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1157199 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1351098 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1229667 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3576. Min Act: -0.0000

Data Index: 273330 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2673. Min Act: -0.0000

Data Index: 469657 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1135159 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3243. Min Act: -0.0000

Data Index: 509944 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.3123. Min Act: -0.0000

Data Index: 28861 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2905. Min Act: -0.0000

Data Index: 707773 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2910. Min Act: -0.0000

Data Index: 5961 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1201001 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1220491 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1340200 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.2861. Min Act: -0.0000

Data Index: 784026 (C4 (Web Text))

Max Activating Token Index: 500