Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.1009. Min Act: -0.0001

Data Index: 628952 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0510. Min Act: -0.0001

Data Index: 258896 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0994. Min Act: -0.0001

Data Index: 790740 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0735. Min Act: -0.0001

Data Index: 552484 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9196. Min Act: -0.0001

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9972. Min Act: -0.0001

Data Index: 299606 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1208328 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.1009. Min Range: -1.1009

Max Act: 1.0377. Min Act: -0.0001

Data Index: 658514 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8205. Min Act: -0.0001

Data Index: 140988 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9717. Min Act: -0.0001

Data Index: 197117 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9705. Min Act: -0.0001

Data Index: 528343 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1298988 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9228. Min Act: -0.0001

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9546. Min Act: -0.0001

Data Index: 158810 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8981. Min Act: -0.0001

Data Index: 23632 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9207. Min Act: -0.0001

Data Index: 1346249 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1299232 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8822. Min Act: -0.0001

Data Index: 769388 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9324. Min Act: -0.0001

Data Index: 1211017 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9299. Min Act: -0.0001

Data Index: 791180 (C4 (Web Text))

Max Activating Token Index: 525