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

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

Neuron 479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0267. Min Range: -3.0267

Max Act: 3.0267. Min Act: -0.0001

Data Index: 774223 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.9644. Min Act: -0.0001

Data Index: 234656 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.9618. Min Act: -0.0001

Data Index: 692140 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.5617. Min Act: -0.0001

Data Index: 207190 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.6832. Min Act: -0.0001

Data Index: 669596 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.7672. Min Act: -0.0001

Data Index: 1125234 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.6162. Min Act: -0.0001

Data Index: 59589 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.8701. Min Act: -0.0001

Data Index: 577863 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.5928. Min Act: -0.0001

Data Index: 147210 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.6911. Min Act: -0.0001

Data Index: 304487 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.5841. Min Act: -0.0001

Data Index: 1178015 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.4381. Min Act: -0.0001

Data Index: 1239423 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.2863. Min Act: -0.0001

Data Index: 120528 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.4110. Min Act: -0.0001

Data Index: 137358 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.5007. Min Act: -0.0001

Data Index: 1188026 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.5983. Min Act: -0.0001

Data Index: 10878 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.7186. Min Act: -0.0001

Data Index: 455088 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.4684. Min Act: -0.0001

Data Index: 536235 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.4178. Min Act: -0.0001

Data Index: 1175334 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.0267. Min Range: -3.0267

Max Act: 2.4492. Min Act: -0.0001

Data Index: 1299536 (C4 (Web Text))

Max Activating Token Index: 113