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

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

Neuron 217 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: 0.4055. Min Range: -0.4055

Max Act: 0.4055. Min Act: -0.0002

Data Index: 439572 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3694. Min Act: -0.0002

Data Index: 612365 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3864. Min Act: -0.0002

Data Index: 735632 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3378. Min Act: -0.0002

Data Index: 878189 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3370. Min Act: -0.0002

Data Index: 231994 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3340. Min Act: -0.0002

Data Index: 1167650 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3127. Min Act: -0.0002

Data Index: 762673 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3133. Min Act: -0.0002

Data Index: 1359422 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3075. Min Act: -0.0002

Data Index: 611494 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3181. Min Act: -0.0002

Data Index: 984604 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3126. Min Act: -0.0002

Data Index: 815900 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3008. Min Act: -0.0002

Data Index: 1219037 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2872. Min Act: -0.0002

Data Index: 1076416 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2991. Min Act: -0.0002

Data Index: 645906 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2831. Min Act: -0.0002

Data Index: 838135 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2863. Min Act: -0.0002

Data Index: 894395 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2603. Min Act: -0.0002

Data Index: 757140 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2752. Min Act: -0.0002

Data Index: 956155 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.3074. Min Act: -0.0002

Data Index: 929718 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.4055. Min Range: -0.4055

Max Act: 0.2898. Min Act: -0.0002

Data Index: 937510 (C4 (Web Text))

Max Activating Token Index: 74