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

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

Neuron 1545 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: 5.2274. Min Range: -5.2274

Max Act: 5.2274. Min Act: -0.1700

Data Index: 1561998 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.2018. Min Act: -0.1700

Data Index: 1486627 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.1901. Min Act: -0.1700

Data Index: 1441198 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.1073. Min Act: -0.1700

Data Index: 1530851 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0411. Min Act: -0.1700

Data Index: 1502846 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0787. Min Act: -0.1700

Data Index: 1408574 (Python Code)

Max Activating Token Index: 326

Text #6

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0684. Min Act: -0.1700

Data Index: 1512653 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0271. Min Act: -0.1700

Data Index: 1610173 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0990. Min Act: -0.1700

Data Index: 1505721 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0208. Min Act: -0.1700

Data Index: 1431117 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0080. Min Act: -0.1700

Data Index: 1540822 (Python Code)

Max Activating Token Index: 518

Text #11

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9592. Min Act: -0.1700

Data Index: 1651099 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9991. Min Act: -0.1700

Data Index: 1632091 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 5.2274. Min Range: -5.2274

Max Act: 5.0049. Min Act: -0.1700

Data Index: 1485335 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9542. Min Act: -0.1700

Data Index: 1402045 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1366903 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9103. Min Act: -0.1700

Data Index: 1603581 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9490. Min Act: -0.1700

Data Index: 1633013 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.8788. Min Act: -0.1700

Data Index: 1440970 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 5.2274. Min Range: -5.2274

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1580554 (Python Code)

Max Activating Token Index: 999