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

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

Neuron 3988 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5418. Min Act: -0.0001

Data Index: 404752 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4878. Min Act: -0.0000

Data Index: 642692 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1144091 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4781. Min Act: -0.0001

Data Index: 403891 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4555. Min Act: -0.0001

Data Index: 846289 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4691. Min Act: -0.0001

Data Index: 80231 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1038798 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1190334 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.5251. Min Act: -0.0001

Data Index: 754252 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4284. Min Act: -0.0000

Data Index: 179508 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4182. Min Act: -0.0001

Data Index: 612903 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4011. Min Act: -0.0001

Data Index: 589127 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4127. Min Act: -0.0000

Data Index: 558496 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4192. Min Act: -0.0001

Data Index: 229040 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4233. Min Act: -0.0001

Data Index: 96402 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4023. Min Act: -0.0001

Data Index: 580725 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4154. Min Act: -0.0001

Data Index: 387095 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4095. Min Act: -0.0000

Data Index: 104533 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1254956 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.5418. Min Range: -0.5418

Max Act: 0.4115. Min Act: -0.0001

Data Index: 180901 (C4 (Web Text))

Max Activating Token Index: 243