Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0694. Min Range: -3.0694

Max Act: 3.0694. Min Act: -0.0000

Data Index: 337503 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.0694. Min Range: -3.0694

Max Act: 3.0391. Min Act: -0.0000

Data Index: 637127 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.7625. Min Act: -0.0000

Data Index: 1140998 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.7641. Min Act: -0.0001

Data Index: 187459 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.6055. Min Act: -0.0001

Data Index: 320581 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.5906. Min Act: -0.0001

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.7588. Min Act: -0.0000

Data Index: 1172002 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4321. Min Act: -0.0000

Data Index: 1117817 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.6774. Min Act: -0.0001

Data Index: 35718 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4817. Min Act: -0.0001

Data Index: 1323137 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.6113. Min Act: -0.0000

Data Index: 1324826 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1288983 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4347. Min Act: -0.0001

Data Index: 171365 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.5658. Min Act: -0.0000

Data Index: 350842 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4755. Min Act: -0.0001

Data Index: 1001498 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4549. Min Act: -0.0000

Data Index: 631567 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.3318. Min Act: -0.0001

Data Index: 1019284 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.4208. Min Act: -0.0001

Data Index: 549424 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.3654. Min Act: -0.0000

Data Index: 751308 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.3698. Min Act: -0.0001

Data Index: 1193191 (C4 (Web Text))

Max Activating Token Index: 42