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

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

Neuron 4653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.4122. Min Act: -0.0000

Data Index: 927225 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.9489. Min Act: -0.0000

Data Index: 421224 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.6529. Min Act: -0.0000

Data Index: 779381 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.6496. Min Act: -0.0000

Data Index: 416407 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.4572. Min Act: -0.0000

Data Index: 1202116 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.4047. Min Act: -0.0000

Data Index: 710394 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.3580. Min Act: -0.0000

Data Index: 1227906 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.2407. Min Act: -0.0000

Data Index: 1240 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.9708. Min Act: -0.0000

Data Index: 411788 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.9781. Min Act: -0.0000

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.9813. Min Act: -0.0000

Data Index: 489183 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0575. Min Act: -0.0000

Data Index: 358415 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0406. Min Act: -0.0000

Data Index: 1302146 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0526. Min Act: -0.0000

Data Index: 965492 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0162. Min Act: -0.0000

Data Index: 725894 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1238674 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.4122. Min Range: -3.4122

Max Act: 2.0221. Min Act: -0.0000

Data Index: 769703 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.8793. Min Act: -0.0000

Data Index: 41961 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 3.4122. Min Range: -3.4122

Max Act: 1.9711. Min Act: -0.0000

Data Index: 838982 (C4 (Web Text))

Max Activating Token Index: 487