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

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

Neuron 3529 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0001

Data Index: 556111 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2468. Min Act: -0.0001

Data Index: 437856 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3089. Min Act: -0.0001

Data Index: 390024 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2855. Min Act: -0.0001

Data Index: 1272761 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1523. Min Act: -0.0001

Data Index: 721168 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0783. Min Act: -0.0001

Data Index: 1251527 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1233581 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0992. Min Act: -0.0001

Data Index: 73824 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9376. Min Act: -0.0001

Data Index: 542712 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0135. Min Act: -0.0001

Data Index: 579095 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0001. Min Act: -0.0001

Data Index: 520242 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0326. Min Act: -0.0001

Data Index: 449421 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0882. Min Act: -0.0001

Data Index: 1159650 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9652. Min Act: -0.0001

Data Index: 293396 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9563. Min Act: -0.0001

Data Index: 773241 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0180. Min Act: -0.0001

Data Index: 87579 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.0052. Min Act: -0.0001

Data Index: 736088 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1628. Min Act: -0.0001

Data Index: 1033442 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9962. Min Act: -0.0001

Data Index: 913904 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9349. Min Act: -0.0001

Data Index: 409912 (C4 (Web Text))

Max Activating Token Index: 230