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

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

Neuron 1799 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: 3.2281. Min Range: -3.2281

Max Act: 3.2281. Min Act: -0.1700

Data Index: 1488747 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1536536 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1568105 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1450830 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1402003 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1021. Min Act: -0.1700

Data Index: 1435370 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.1021. Min Act: -0.1700

Data Index: 1436358 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.0548. Min Act: -0.1700

Data Index: 1572323 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.0548. Min Act: -0.1700

Data Index: 1534975 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.0074. Min Act: -0.1700

Data Index: 388977 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9916. Min Act: -0.1700

Data Index: 1629060 (Python Code)

Max Activating Token Index: 971

Text #11

Max Range: 3.2281. Min Range: -3.2281

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1369801 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9758. Min Act: -0.1700

Data Index: 1604395 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9599. Min Act: -0.1700

Data Index: 853492 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9758. Min Act: -0.1700

Data Index: 1445838 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9441. Min Act: -0.1700

Data Index: 1562900 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9283. Min Act: -0.1700

Data Index: 1649883 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9124. Min Act: -0.1700

Data Index: 307431 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.8965. Min Act: -0.1700

Data Index: 1623411 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 3.2281. Min Range: -3.2281

Max Act: 2.9124. Min Act: -0.1700

Data Index: 1392988 (Python Code)

Max Activating Token Index: 39