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

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

Neuron 4480 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.7025. Min Act: -0.0001

Data Index: 1567810 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.6585. Min Act: -0.0001

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.6560. Min Act: -0.0001

Data Index: 1311377 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.6102. Min Act: -0.0001

Data Index: 78166 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4810. Min Act: -0.0001

Data Index: 954768 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.3476. Min Act: -0.0001

Data Index: 1216340 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4244. Min Act: -0.0001

Data Index: 917426 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.5202. Min Act: -0.0001

Data Index: 762704 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.5702. Min Act: -0.0001

Data Index: 1265947 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4404. Min Act: -0.0000

Data Index: 948803 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4357. Min Act: -0.0001

Data Index: 106575 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1869. Min Act: -0.0001

Data Index: 1058275 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4193. Min Act: -0.0001

Data Index: 514224 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4190. Min Act: -0.0001

Data Index: 347829 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.3237. Min Act: -0.0001

Data Index: 1537135 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.3176. Min Act: -0.0001

Data Index: 254248 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.3723. Min Act: -0.0001

Data Index: 1117099 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.2879. Min Act: -0.0001

Data Index: 882198 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4569. Min Act: -0.0001

Data Index: 792862 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.3434. Min Act: -0.0001

Data Index: 841261 (C4 (Web Text))

Max Activating Token Index: 1012