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

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

Neuron 5596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4178. Min Range: -3.4178

Max Act: 3.4178. Min Act: -0.0001

Data Index: 20896 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 3.4178. Min Range: -3.4178

Max Act: 3.3181. Min Act: -0.0001

Data Index: 675057 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.4178. Min Range: -3.4178

Max Act: 3.3228. Min Act: -0.0000

Data Index: 1142070 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.9970. Min Act: -0.0000

Data Index: 1262891 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.7988. Min Act: -0.0001

Data Index: 492100 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.9403. Min Act: -0.0001

Data Index: 287109 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.7261. Min Act: -0.0001

Data Index: 71792 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.7162. Min Act: -0.0001

Data Index: 664723 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.2970. Min Act: -0.0000

Data Index: 1158254 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.5414. Min Act: -0.0001

Data Index: 959137 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.5185. Min Act: -0.0001

Data Index: 61721 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.4855. Min Act: -0.0001

Data Index: 400758 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.3985. Min Act: -0.0001

Data Index: 62686 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.4009. Min Act: -0.0001

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.2324. Min Act: -0.0000

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.3041. Min Act: -0.0001

Data Index: 676945 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.4274. Min Act: -0.0000

Data Index: 108005 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.0934. Min Act: -0.0001

Data Index: 306341 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.2613. Min Act: -0.0000

Data Index: 1207645 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 3.4178. Min Range: -3.4178

Max Act: 2.1168. Min Act: -0.0001

Data Index: 1140542 (C4 (Web Text))

Max Activating Token Index: 734