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

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

Neuron 1195 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.7783. Min Act: -0.0002

Data Index: 71996 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.7068. Min Act: -0.0003

Data Index: 722103 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.7238. Min Act: -0.0003

Data Index: 662900 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.7033. Min Act: -0.0003

Data Index: 1198308 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.6755. Min Act: -0.0003

Data Index: 1136130 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.6434. Min Act: -0.0003

Data Index: 656919 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.6170. Min Act: -0.0003

Data Index: 1301797 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.6183. Min Act: -0.0002

Data Index: 978446 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5980. Min Act: -0.0003

Data Index: 354202 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5694. Min Act: -0.0002

Data Index: 40115 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5811. Min Act: -0.0003

Data Index: 504082 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5600. Min Act: -0.0003

Data Index: 20154 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5761. Min Act: -0.0003

Data Index: 1140798 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5861. Min Act: -0.0003

Data Index: 332622 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5471. Min Act: -0.0002

Data Index: 1242511 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5580. Min Act: -0.0002

Data Index: 698842 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5649. Min Act: -0.0003

Data Index: 438433 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5616. Min Act: -0.0002

Data Index: 1124332 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5602. Min Act: -0.0002

Data Index: 105289 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.7783. Min Range: -0.7783

Max Act: 0.5743. Min Act: -0.0002

Data Index: 412785 (C4 (Web Text))

Max Activating Token Index: 618