Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 713 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.8173. Min Act: -0.0002

Data Index: 1559130 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.7432. Min Act: -0.0002

Data Index: 1579595 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6292. Min Act: -0.0001

Data Index: 1406582 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6649. Min Act: -0.0002

Data Index: 1459133 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6547. Min Act: -0.0002

Data Index: 1436366 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6009. Min Act: -0.0002

Data Index: 1503790 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1650953 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5634. Min Act: -0.0002

Data Index: 1440112 (Python Code)

Max Activating Token Index: 557

Text #8

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5535. Min Act: -0.0002

Data Index: 1394963 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5720. Min Act: -0.0002

Data Index: 1388719 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5275. Min Act: -0.0002

Data Index: 1656010 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5282. Min Act: -0.0001

Data Index: 1463826 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5470. Min Act: -0.0001

Data Index: 1642152 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5422. Min Act: -0.0002

Data Index: 1392123 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5002. Min Act: -0.0002

Data Index: 1461029 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5184. Min Act: -0.0002

Data Index: 1428466 (Python Code)

Max Activating Token Index: 355

Text #16

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.4861. Min Act: -0.0001

Data Index: 1647175 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.4688. Min Act: -0.0002

Data Index: 1548487 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5069. Min Act: -0.0001

Data Index: 1453376 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.8173. Min Range: -0.8173

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1633474 (Python Code)

Max Activating Token Index: 591