Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 951 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.3258. Min Act: -0.1700

Data Index: 1551610 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.3258. Min Act: -0.1700

Data Index: 1395710 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.2633. Min Act: -0.1700

Data Index: 388562 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.2008. Min Act: -0.1700

Data Index: 1601178 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.1695. Min Act: -0.1700

Data Index: 1287567 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0445. Min Act: -0.1700

Data Index: 1477561 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0758. Min Act: -0.1700

Data Index: 1622106 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0758. Min Act: -0.1700

Data Index: 755612 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0133. Min Act: -0.1700

Data Index: 1411287 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0133. Min Act: -0.1700

Data Index: 319108 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0445. Min Act: -0.1700

Data Index: 1389281 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0445. Min Act: -0.1700

Data Index: 1649049 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9820. Min Act: -0.1700

Data Index: 1447979 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9820. Min Act: -0.1700

Data Index: 1602494 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 7.3258. Min Range: -7.3258

Max Act: 7.0133. Min Act: -0.1700

Data Index: 1596182 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9195. Min Act: -0.1700

Data Index: 1563397 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9508. Min Act: -0.1700

Data Index: 1545900 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9508. Min Act: -0.1700

Data Index: 1484648 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9195. Min Act: -0.1700

Data Index: 1602017 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 7.3258. Min Range: -7.3258

Max Act: 6.9508. Min Act: -0.1700

Data Index: 348759 (C4 (Web Text))

Max Activating Token Index: 483