Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0003

Data Index: 677508 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0959. Min Act: -0.0003

Data Index: 782069 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1149. Min Act: -0.0003

Data Index: 124448 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1034. Min Act: -0.0003

Data Index: 362342 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0835. Min Act: -0.0003

Data Index: 683577 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0910. Min Act: -0.0003

Data Index: 9856 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1275718 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0920. Min Act: -0.0003

Data Index: 797100 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1078731 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1349581 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1117480 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0843. Min Act: -0.0003

Data Index: 709735 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0664. Min Act: -0.0003

Data Index: 764905 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1343758 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1422709 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0744. Min Act: -0.0003

Data Index: 883574 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0826. Min Act: -0.0003

Data Index: 1089745 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1332337 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0751. Min Act: -0.0003

Data Index: 993506 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0721. Min Act: -0.0003

Data Index: 987252 (C4 (Web Text))

Max Activating Token Index: 398