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

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

Neuron 1139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6683. Min Act: -0.0001

Data Index: 676501 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6748. Min Act: -0.0001

Data Index: 839443 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6401. Min Act: -0.0001

Data Index: 601602 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5921. Min Act: -0.0001

Data Index: 889019 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5737. Min Act: -0.0001

Data Index: 496516 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5911. Min Act: -0.0001

Data Index: 339604 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5551. Min Act: -0.0001

Data Index: 621384 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5861. Min Act: -0.0001

Data Index: 527465 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1036139 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5513. Min Act: -0.0001

Data Index: 980072 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1295352 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.4963. Min Act: -0.0001

Data Index: 996273 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5479. Min Act: -0.0001

Data Index: 571902 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5273. Min Act: -0.0001

Data Index: 1170797 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5839. Min Act: -0.0001

Data Index: 177529 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5016. Min Act: -0.0001

Data Index: 147779 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.4665. Min Act: -0.0001

Data Index: 884880 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5310. Min Act: -0.0001

Data Index: 366145 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5235. Min Act: -0.0001

Data Index: 715341 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.4861. Min Act: -0.0001

Data Index: 66474 (C4 (Web Text))

Max Activating Token Index: 370