Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2747 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1592. Min Act: -0.0001

Data Index: 568944 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1359. Min Act: -0.0001

Data Index: 305480 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1402. Min Act: -0.0001

Data Index: 586201 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1442. Min Act: -0.0001

Data Index: 349917 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1123260 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1510. Min Act: -0.0001

Data Index: 877827 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1383. Min Act: -0.0001

Data Index: 794519 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1333. Min Act: -0.0001

Data Index: 768787 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1246. Min Act: -0.0001

Data Index: 49727 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1196. Min Act: -0.0001

Data Index: 379500 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1269578 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1103517 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1229096 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1146. Min Act: -0.0001

Data Index: 290135 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1229. Min Act: -0.0001

Data Index: 682138 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1269. Min Act: -0.0001

Data Index: 846978 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1087. Min Act: -0.0001

Data Index: 639710 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1266. Min Act: -0.0001

Data Index: 384964 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1052682 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1025544 (C4 (Web Text))

Max Activating Token Index: 45