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

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

Neuron 4167 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6752. Min Act: -0.0000

Data Index: 1293995 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6392. Min Act: -0.0000

Data Index: 831177 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6231. Min Act: -0.0000

Data Index: 982302 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1127690 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6212. Min Act: -0.0000

Data Index: 140696 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6072. Min Act: -0.0000

Data Index: 360171 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5942. Min Act: -0.0000

Data Index: 646883 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6759. Min Act: -0.0000

Data Index: 1081585 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.4799. Min Act: -0.0000

Data Index: 895894 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1200127 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.6371. Min Act: -0.0000

Data Index: 396213 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1341764 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1244106 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5231. Min Act: -0.0000

Data Index: 305322 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1213596 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.4953. Min Act: -0.0000

Data Index: 367336 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1117005 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5667. Min Act: -0.0000

Data Index: 914349 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1288430 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.6759. Min Range: -1.6759

Max Act: 1.5384. Min Act: -0.0000

Data Index: 759593 (C4 (Web Text))

Max Activating Token Index: 377