Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 234 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3180. Min Act: -0.0002

Data Index: 184671 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3135. Min Act: -0.0002

Data Index: 444663 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3081. Min Act: -0.0002

Data Index: 277111 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3037. Min Act: -0.0002

Data Index: 845248 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2860. Min Act: -0.0002

Data Index: 295554 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2917. Min Act: -0.0002

Data Index: 1251000 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2944. Min Act: -0.0002

Data Index: 1026347 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2980. Min Act: -0.0002

Data Index: 666320 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2516. Min Act: -0.0002

Data Index: 70641 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2697. Min Act: -0.0002

Data Index: 1246170 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2792. Min Act: -0.0002

Data Index: 1258952 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2614. Min Act: -0.0002

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2701. Min Act: -0.0002

Data Index: 1230664 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2718. Min Act: -0.0002

Data Index: 1195941 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2650. Min Act: -0.0002

Data Index: 301142 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2815. Min Act: -0.0002

Data Index: 1126825 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2652. Min Act: -0.0002

Data Index: 1024390 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2640. Min Act: -0.0002

Data Index: 193757 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2810. Min Act: -0.0002

Data Index: 411830 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2500. Min Act: -0.0002

Data Index: 497953 (C4 (Web Text))

Max Activating Token Index: 81