Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1318484 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.5181. Min Act: -0.0000

Data Index: 289083 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.5201. Min Act: -0.0000

Data Index: 199773 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1091154 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4471. Min Act: -0.0000

Data Index: 351470 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4525. Min Act: 0.0000

Data Index: 369417 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4291. Min Act: -0.0000

Data Index: 472002 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4124. Min Act: 0.0000

Data Index: 652109 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4093. Min Act: -0.0000

Data Index: 464034 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1217384 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3983. Min Act: -0.0000

Data Index: 414291 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3840. Min Act: -0.0000

Data Index: 802691 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.4033. Min Act: -0.0000

Data Index: 505176 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3901. Min Act: -0.0000

Data Index: 153992 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3775. Min Act: -0.0000

Data Index: 987799 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1254470 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3826. Min Act: -0.0000

Data Index: 14560 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1113234 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1042697 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.5392. Min Range: -0.5392

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1340858 (C4 (Web Text))

Max Activating Token Index: 732