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

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

Neuron 3528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7732. Min Act: -0.0001

Data Index: 328804 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7120. Min Act: -0.0001

Data Index: 960235 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1330313 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5247. Min Act: -0.0001

Data Index: 1094575 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5198. Min Act: -0.0001

Data Index: 626420 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5212. Min Act: -0.0001

Data Index: 530898 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5321. Min Act: -0.0002

Data Index: 397142 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1074184 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5089. Min Act: -0.0001

Data Index: 611339 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5124. Min Act: -0.0002

Data Index: 782990 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4993. Min Act: -0.0002

Data Index: 1221813 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4813. Min Act: -0.0001

Data Index: 988217 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5265. Min Act: -0.0002

Data Index: 248787 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4236. Min Act: -0.0001

Data Index: 980979 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4557. Min Act: -0.0002

Data Index: 1342406 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5200. Min Act: -0.0001

Data Index: 893894 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4479. Min Act: -0.0002

Data Index: 1267360 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4759. Min Act: -0.0001

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4664. Min Act: -0.0001

Data Index: 203478 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4496. Min Act: -0.0001

Data Index: 460336 (C4 (Web Text))

Max Activating Token Index: 198