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

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

Neuron 2449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6695. Min Act: -0.0001

Data Index: 895237 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.7211. Min Act: -0.0001

Data Index: 1325424 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6712. Min Act: -0.0001

Data Index: 341089 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6279. Min Act: -0.0001

Data Index: 1374967 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6358. Min Act: -0.0001

Data Index: 1530402 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6141. Min Act: -0.0001

Data Index: 11841 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1517907 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.6026. Min Act: -0.0001

Data Index: 330587 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5745. Min Act: -0.0001

Data Index: 773701 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5910. Min Act: -0.0001

Data Index: 794078 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5696. Min Act: -0.0001

Data Index: 795050 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5481. Min Act: -0.0001

Data Index: 1252777 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5741. Min Act: -0.0001

Data Index: 1041889 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1648328 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5356. Min Act: -0.0001

Data Index: 169247 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5455. Min Act: -0.0001

Data Index: 1103788 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1577262 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5134. Min Act: -0.0001

Data Index: 515163 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1464194 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.7211. Min Range: -0.7211

Max Act: 0.5226. Min Act: -0.0001

Data Index: 76820 (C4 (Web Text))

Max Activating Token Index: 779