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

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

Neuron 5465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1555975 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1522956 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.3674. Min Act: -0.0000

Data Index: 845569 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1538373 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1365742 (Python Code)

Max Activating Token Index: 631

Text #5

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1374343 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2944. Min Act: -0.0000

Data Index: 19174 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1570371 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1100728 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1654175 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1623429 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2681. Min Act: -0.0000

Data Index: 627632 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1466441 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1036174 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1395984 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1500149 (Python Code)

Max Activating Token Index: 314

Text #16

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1043550 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1515189 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1475639 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 1.8397. Min Range: -1.8397

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1128456 (C4 (Web Text))

Max Activating Token Index: 272