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

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

Neuron 375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.8393. Min Act: -0.1700

Data Index: 1392992 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.8393. Min Act: -0.1700

Data Index: 1634412 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.8393. Min Act: -0.1700

Data Index: 1534641 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.7455. Min Act: -0.1700

Data Index: 1432431 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.7767. Min Act: -0.1700

Data Index: 1461502 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1363339 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.7142. Min Act: -0.1700

Data Index: 1430239 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1441192 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1545807 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 1492622 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.7142. Min Act: -0.1700

Data Index: 1570905 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6203. Min Act: -0.1700

Data Index: 1482693 (Python Code)

Max Activating Token Index: 998

Text #12

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1369764 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1586276 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 1546941 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6203. Min Act: -0.1700

Data Index: 1586531 (Python Code)

Max Activating Token Index: 413

Text #16

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 1401470 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 1473833 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6829. Min Act: -0.1700

Data Index: 1498901 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 1387241 (Python Code)

Max Activating Token Index: 313