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

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

Neuron 2450 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: 0.0962. Min Range: -0.0962

Max Act: 0.0925. Min Act: -0.0001

Data Index: 734369 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0912. Min Act: -0.0001

Data Index: 277535 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1197583 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0962. Min Act: -0.0001

Data Index: 708812 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1145076 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0921. Min Act: -0.0001

Data Index: 92969 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0916. Min Act: -0.0001

Data Index: 149770 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1263642 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0814. Min Act: -0.0001

Data Index: 166216 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0816. Min Act: -0.0001

Data Index: 122094 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0852. Min Act: -0.0001

Data Index: 917378 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1302333 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1045512 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1300834 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1276804 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1121809 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1207540 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0847. Min Act: -0.0001

Data Index: 468734 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0892. Min Act: -0.0001

Data Index: 776326 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0756. Min Act: -0.0001

Data Index: 470115 (C4 (Web Text))

Max Activating Token Index: 499