Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6337. Min Act: -0.0000

Data Index: 863934 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6190. Min Act: -0.0000

Data Index: 234143 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5695. Min Act: -0.0001

Data Index: 1139950 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1162043 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6813. Min Act: -0.0000

Data Index: 90484 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5159. Min Act: -0.0001

Data Index: 779925 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5221. Min Act: -0.0000

Data Index: 856699 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5105. Min Act: -0.0000

Data Index: 209365 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5384. Min Act: -0.0000

Data Index: 600399 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4944. Min Act: -0.0000

Data Index: 437596 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5142. Min Act: -0.0000

Data Index: 9644 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1300810 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4711. Min Act: -0.0000

Data Index: 42005 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5027. Min Act: -0.0000

Data Index: 549847 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4725. Min Act: -0.0000

Data Index: 313773 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4807. Min Act: -0.0000

Data Index: 921115 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1055324 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4755. Min Act: -0.0000

Data Index: 517445 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4728. Min Act: -0.0000

Data Index: 978952 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4762. Min Act: -0.0000

Data Index: 291274 (C4 (Web Text))

Max Activating Token Index: 114