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

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

Neuron 999 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.8003. Min Act: -0.0000

Data Index: 264030 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.7870. Min Act: -0.0000

Data Index: 917897 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.7070. Min Act: -0.0000

Data Index: 709973 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.5231. Min Act: -0.0000

Data Index: 586102 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.3216. Min Act: -0.0000

Data Index: 1137011 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1040695 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1076959 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.2047. Min Act: -0.0001

Data Index: 801180 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.1382. Min Act: -0.0000

Data Index: 1033769 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.1949. Min Act: -0.0000

Data Index: 1237749 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.0893. Min Act: -0.0000

Data Index: 848096 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.0662. Min Act: -0.0000

Data Index: 288388 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.8668. Min Act: -0.0000

Data Index: 898359 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.9208. Min Act: -0.0000

Data Index: 549603 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.1375. Min Act: -0.0000

Data Index: 962401 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.8003. Min Range: -2.8003

Max Act: 2.1239. Min Act: -0.0000

Data Index: 240827 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.9018. Min Act: -0.0000

Data Index: 48216 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.9935. Min Act: -0.0000

Data Index: 311775 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.8651. Min Act: -0.0000

Data Index: 789924 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.8003. Min Range: -2.8003

Max Act: 1.8584. Min Act: -0.0001

Data Index: 898384 (C4 (Web Text))

Max Activating Token Index: 558