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

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

Neuron 3896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.7285. Min Act: -0.0000

Data Index: 580076 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.6868. Min Act: -0.0000

Data Index: 229099 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.6096. Min Act: -0.0000

Data Index: 810769 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1305138 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5464. Min Act: -0.0000

Data Index: 17151 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1081803 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5501. Min Act: -0.0000

Data Index: 558430 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5305. Min Act: -0.0000

Data Index: 776754 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5337. Min Act: -0.0000

Data Index: 652042 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5251. Min Act: -0.0000

Data Index: 715047 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5321. Min Act: -0.0000

Data Index: 40752 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4939. Min Act: -0.0000

Data Index: 68419 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5125. Min Act: -0.0000

Data Index: 432629 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4734. Min Act: -0.0000

Data Index: 201762 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4914. Min Act: -0.0000

Data Index: 97056 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1240781 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.5171. Min Act: -0.0000

Data Index: 227054 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4949. Min Act: -0.0000

Data Index: 307582 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1158833 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.7285. Min Range: -0.7285

Max Act: 0.4547. Min Act: -0.0000

Data Index: 246007 (C4 (Web Text))

Max Activating Token Index: 455