Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1486 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5253. Min Act: -0.0001

Data Index: 410741 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5186. Min Act: -0.0001

Data Index: 716310 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4765. Min Act: -0.0001

Data Index: 102418 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4820. Min Act: -0.0001

Data Index: 231884 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4718. Min Act: -0.0001

Data Index: 485930 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1268576 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4532. Min Act: -0.0001

Data Index: 758648 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4334. Min Act: -0.0001

Data Index: 423575 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4266. Min Act: -0.0001

Data Index: 521562 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4279. Min Act: -0.0001

Data Index: 1314679 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4401. Min Act: -0.0001

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4135. Min Act: -0.0001

Data Index: 83866 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4242. Min Act: -0.0001

Data Index: 467977 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4455. Min Act: -0.0001

Data Index: 181286 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4193. Min Act: -0.0001

Data Index: 1270918 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4082. Min Act: -0.0001

Data Index: 823472 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4475. Min Act: -0.0001

Data Index: 731483 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4109. Min Act: -0.0001

Data Index: 455902 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4044. Min Act: -0.0001

Data Index: 449969 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1236999 (C4 (Web Text))

Max Activating Token Index: 465