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

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

Neuron 5897 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4260. Min Range: -4.4260

Max Act: 4.4260. Min Act: -0.0000

Data Index: 1139897 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 4.4260. Min Range: -4.4260

Max Act: 3.7172. Min Act: -0.0000

Data Index: 1178756 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 4.4260. Min Range: -4.4260

Max Act: 3.6746. Min Act: -0.0000

Data Index: 1204287 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 4.4260. Min Range: -4.4260

Max Act: 3.4576. Min Act: -0.0000

Data Index: 1169571 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 4.4260. Min Range: -4.4260

Max Act: 3.4483. Min Act: -0.0000

Data Index: 195080 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 4.4260. Min Range: -4.4260

Max Act: 3.3621. Min Act: -0.0000

Data Index: 1279820 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.9620. Min Act: -0.0000

Data Index: 784480 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.8305. Min Act: -0.0000

Data Index: 959407 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.6896. Min Act: -0.0000

Data Index: 396844 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.9189. Min Act: -0.0000

Data Index: 1216137 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.9260. Min Act: -0.0000

Data Index: 567830 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.9217. Min Act: -0.0000

Data Index: 391459 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.9159. Min Act: -0.0000

Data Index: 1261805 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.7672. Min Act: -0.0000

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.8901. Min Act: -0.0000

Data Index: 822899 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.8174. Min Act: -0.0000

Data Index: 965100 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.8222. Min Act: -0.0000

Data Index: 82006 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.7988. Min Act: -0.0000

Data Index: 646843 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.6308. Min Act: -0.0000

Data Index: 681018 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 4.4260. Min Range: -4.4260

Max Act: 2.4745. Min Act: -0.0000

Data Index: 312725 (C4 (Web Text))

Max Activating Token Index: 541