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

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

Neuron 277 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.2171. Min Act: -0.0003

Data Index: 274169 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1577. Min Act: -0.0003

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1162. Min Act: -0.0003

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1117. Min Act: -0.0003

Data Index: 473350 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1065. Min Act: -0.0003

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1012. Min Act: -0.0003

Data Index: 812845 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1193272 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0990. Min Act: -0.0003

Data Index: 283262 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0979. Min Act: -0.0003

Data Index: 748466 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0961. Min Act: -0.0003

Data Index: 1035660 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1183676 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0953. Min Act: -0.0003

Data Index: 458855 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0949. Min Act: -0.0003

Data Index: 608122 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0926. Min Act: -0.0003

Data Index: 80593 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0910. Min Act: -0.0003

Data Index: 373201 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0889. Min Act: -0.0003

Data Index: 792018 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0854. Min Act: -0.0003

Data Index: 686443 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1018799 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.0858. Min Act: -0.0003

Data Index: 579246 (C4 (Web Text))

Max Activating Token Index: 185