Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1243 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.5232. Min Act: -0.1700

Data Index: 1401123 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.4341. Min Act: -0.1700

Data Index: 1613273 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3915. Min Act: -0.1700

Data Index: 1530820 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3327. Min Act: -0.1700

Data Index: 1597610 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3196. Min Act: -0.1700

Data Index: 1548122 (Python Code)

Max Activating Token Index: 814

Text #5

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3134. Min Act: -0.1700

Data Index: 1540333 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1383447 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3071. Min Act: -0.1700

Data Index: 1602633 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.3049. Min Act: -0.1700

Data Index: 1527725 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1372143 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2848. Min Act: -0.1700

Data Index: 1541771 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2472. Min Act: -0.1700

Data Index: 1617423 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2621. Min Act: -0.1700

Data Index: 1467120 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2604. Min Act: -0.1700

Data Index: 1470150 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1626997 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2354. Min Act: -0.1700

Data Index: 1442085 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1381674 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.2012. Min Act: -0.1700

Data Index: 1461805 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.1759. Min Act: -0.1700

Data Index: 1452661 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 3.5232. Min Range: -3.5232

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1391040 (Python Code)

Max Activating Token Index: 467