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

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

Neuron 5986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.7045. Min Act: -0.0000

Data Index: 552794 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1078027 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1306833 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.6140. Min Act: -0.0000

Data Index: 629746 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5825. Min Act: -0.0000

Data Index: 56316 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5406. Min Act: -0.0000

Data Index: 634616 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1016723 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5946. Min Act: -0.0000

Data Index: 572838 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1300502 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5582. Min Act: -0.0000

Data Index: 977493 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5745. Min Act: -0.0000

Data Index: 431877 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5629. Min Act: -0.0000

Data Index: 421076 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5294. Min Act: -0.0000

Data Index: 359795 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4833. Min Act: -0.0000

Data Index: 275400 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1170208 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1331751 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1128710 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4411. Min Act: -0.0000

Data Index: 653727 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1111352 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4518. Min Act: -0.0000

Data Index: 136396 (C4 (Web Text))

Max Activating Token Index: 844