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

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

Neuron 2845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.7014. Min Act: -0.0000

Data Index: 877234 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4146. Min Act: -0.0000

Data Index: 530308 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3820. Min Act: -0.0000

Data Index: 624704 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4291. Min Act: -0.0000

Data Index: 200142 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3951. Min Act: -0.0000

Data Index: 293375 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3898. Min Act: -0.0000

Data Index: 969380 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4100. Min Act: -0.0000

Data Index: 506322 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1101505 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3613. Min Act: -0.0000

Data Index: 674400 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.4184. Min Act: -0.0000

Data Index: 722574 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1249781 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3685. Min Act: -0.0000

Data Index: 250353 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3669. Min Act: -0.0000

Data Index: 184022 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3421. Min Act: -0.0000

Data Index: 791386 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3379. Min Act: -0.0000

Data Index: 959189 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3403. Min Act: -0.0000

Data Index: 52035 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1212760 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3323. Min Act: -0.0000

Data Index: 346922 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1322040 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.7014. Min Range: -0.7014

Max Act: 0.3205. Min Act: -0.0000

Data Index: 99783 (C4 (Web Text))

Max Activating Token Index: 75