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

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

Neuron 1910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1548454 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1416293 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1603630 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1462965 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.4270. Min Act: 0.0000

Data Index: 1451577 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1641545 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1124172 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1606321 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3341. Min Act: -0.0000

Data Index: 458253 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1369038 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1456078 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3591. Min Act: -0.0000

Data Index: 991924 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3055. Min Act: -0.0000

Data Index: 321531 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1551290 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3079. Min Act: 0.0000

Data Index: 1507522 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.3048. Min Act: -0.0000

Data Index: 925876 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1029945 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1427492 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.2297. Min Act: -0.0000

Data Index: 155153 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.5215. Min Range: -1.5215

Max Act: 1.1968. Min Act: -0.0000

Data Index: 111786 (C4 (Web Text))

Max Activating Token Index: 349