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

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

Neuron 3034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.3719. Min Act: -0.0000

Data Index: 1062393 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.3749. Min Act: -0.0000

Data Index: 506041 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.3156. Min Act: -0.0000

Data Index: 563100 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.2694. Min Act: -0.0000

Data Index: 640779 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.3196. Min Act: -0.0000

Data Index: 1007284 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.1971. Min Act: -0.0000

Data Index: 296101 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 3.3749. Min Range: -3.3749

Max Act: 3.1125. Min Act: -0.0000

Data Index: 213542 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.7980. Min Act: -0.0000

Data Index: 110472 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.9431. Min Act: -0.0000

Data Index: 1303702 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.7584. Min Act: -0.0000

Data Index: 838276 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.7089. Min Act: -0.0000

Data Index: 675709 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.8248. Min Act: -0.0000

Data Index: 1039566 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.8467. Min Act: -0.0000

Data Index: 625100 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.6811. Min Act: -0.0000

Data Index: 1162332 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.8240. Min Act: -0.0000

Data Index: 840741 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.5578. Min Act: -0.0000

Data Index: 905882 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.8170. Min Act: -0.0000

Data Index: 992841 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.5247. Min Act: -0.0000

Data Index: 869289 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1321276 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 3.3749. Min Range: -3.3749

Max Act: 2.5701. Min Act: -0.0000

Data Index: 318507 (C4 (Web Text))

Max Activating Token Index: 312