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

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

Neuron 819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3628. Min Act: -0.0002

Data Index: 1537915 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3290. Min Act: -0.0002

Data Index: 1570474 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2296. Min Act: -0.0002

Data Index: 1651591 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1966. Min Act: -0.0002

Data Index: 1403217 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1192. Min Act: -0.0002

Data Index: 1365953 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1258. Min Act: -0.0002

Data Index: 1438830 (Python Code)

Max Activating Token Index: 290

Text #6

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1022. Min Act: -0.0002

Data Index: 1518364 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0936. Min Act: -0.0002

Data Index: 900234 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0788. Min Act: -0.0002

Data Index: 1605203 (Python Code)

Max Activating Token Index: 709

Text #9

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0688. Min Act: -0.0002

Data Index: 1557104 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0549. Min Act: -0.0002

Data Index: 1637767 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0371. Min Act: -0.0002

Data Index: 1511678 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0503. Min Act: -0.0002

Data Index: 1430503 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0274. Min Act: -0.0002

Data Index: 1370035 (Python Code)

Max Activating Token Index: 829

Text #14

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0219. Min Act: -0.0002

Data Index: 1597657 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0240. Min Act: -0.0002

Data Index: 1565431 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0588. Min Act: -0.0002

Data Index: 1650238 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0185. Min Act: -0.0002

Data Index: 1420248 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0347. Min Act: -0.0002

Data Index: 173651 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0499. Min Act: -0.0002

Data Index: 1486362 (Python Code)

Max Activating Token Index: 957