Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.7253. Min Act: -0.1700

Data Index: 1547681 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6940. Min Act: -0.1700

Data Index: 1531499 (Python Code)

Max Activating Token Index: 353

Text #2

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.7097. Min Act: -0.1700

Data Index: 1442687 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1459065 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1391909 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1494386 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6471. Min Act: -0.1700

Data Index: 1438834 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1503786 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1420678 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1558452 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1408580 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1591258 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1500054 (Python Code)

Max Activating Token Index: 125

Text #13

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1640913 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1644481 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1398415 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1494932 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.5688. Min Act: -0.1700

Data Index: 1504560 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1510201 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 3.7253. Min Range: -3.7253

Max Act: 3.5688. Min Act: -0.1700

Data Index: 1398070 (Python Code)

Max Activating Token Index: 436