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

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

Neuron 1612 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.8017. Min Act: -0.0000

Data Index: 68187 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1113039 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5778. Min Act: -0.0000

Data Index: 374554 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5523. Min Act: -0.0000

Data Index: 807299 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5015. Min Act: -0.0000

Data Index: 155560 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5150. Min Act: -0.0000

Data Index: 377332 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1041225 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4552. Min Act: -0.0000

Data Index: 524128 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4240. Min Act: -0.0000

Data Index: 251767 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1209708 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4315. Min Act: -0.0000

Data Index: 878587 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4219. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1085387 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4196. Min Act: -0.0000

Data Index: 745254 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4378. Min Act: -0.0000

Data Index: 437757 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1222053 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.4462. Min Act: -0.0000

Data Index: 222070 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.3748. Min Act: -0.0000

Data Index: 808005 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1117013 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1241043 (C4 (Web Text))

Max Activating Token Index: 649