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

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

Neuron 3386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0694. Min Act: -0.0002

Data Index: 54916 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0828. Min Act: -0.0002

Data Index: 161559 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0503. Min Act: -0.0002

Data Index: 1310004 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0357. Min Act: -0.0002

Data Index: 1214571 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0298. Min Act: -0.0002

Data Index: 81386 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9933. Min Act: -0.0002

Data Index: 615929 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0263. Min Act: -0.0002

Data Index: 470039 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9939. Min Act: -0.0002

Data Index: 1312945 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9957. Min Act: -0.0002

Data Index: 1330647 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9982. Min Act: -0.0002

Data Index: 1348326 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9831. Min Act: -0.0002

Data Index: 736932 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9892. Min Act: -0.0002

Data Index: 382714 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9692. Min Act: -0.0003

Data Index: 1144710 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9594. Min Act: -0.0002

Data Index: 633354 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9464. Min Act: -0.0002

Data Index: 889264 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9656. Min Act: -0.0002

Data Index: 850151 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9536. Min Act: -0.0002

Data Index: 1023834 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9740. Min Act: -0.0002

Data Index: 1338971 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9564. Min Act: -0.0002

Data Index: 419258 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9414. Min Act: -0.0002

Data Index: 246600 (C4 (Web Text))

Max Activating Token Index: 53