Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1995 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1262. Min Act: -0.1700

Data Index: 317598 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1419. Min Act: -0.1700

Data Index: 1598400 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1262. Min Act: -0.1700

Data Index: 1414321 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1262. Min Act: -0.1700

Data Index: 1481268 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1262. Min Act: -0.1700

Data Index: 1484878 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1392237 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1422840 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1487847 (Python Code)

Max Activating Token Index: 298

Text #8

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1613306 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1530594 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1535521 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1547188 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1580726 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1584363 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1586178 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1603416 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1447228 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1397330 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1359890 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0947. Min Act: -0.1700

Data Index: 59220 (C4 (Web Text))

Max Activating Token Index: 73