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

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

Neuron 2980 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2593. Min Range: -2.2593

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1213433 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.8904. Min Act: -0.0000

Data Index: 139991 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6912. Min Act: -0.0000

Data Index: 180203 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6355. Min Act: -0.0000

Data Index: 197374 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1337197 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.7529. Min Act: -0.0000

Data Index: 481442 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6750. Min Act: -0.0000

Data Index: 836388 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5869. Min Act: -0.0000

Data Index: 321133 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6381. Min Act: -0.0000

Data Index: 648237 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6413. Min Act: -0.0000

Data Index: 52276 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5430. Min Act: -0.0000

Data Index: 47779 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5840. Min Act: -0.0000

Data Index: 956963 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.2531. Min Act: -0.0000

Data Index: 411681 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5134. Min Act: -0.0000

Data Index: 742689 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1341704 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.3896. Min Act: -0.0000

Data Index: 634576 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1093211 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5253. Min Act: -0.0000

Data Index: 824692 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1080657 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 2.2593. Min Range: -2.2593

Max Act: 1.5226. Min Act: -0.0000

Data Index: 143575 (C4 (Web Text))

Max Activating Token Index: 751