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

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

Neuron 1732 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: 19.6677. Min Range: -19.6677

Max Act: 19.6677. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 19.6677. Min Range: -19.6677

Max Act: 19.1677. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 19.6677. Min Range: -19.6677

Max Act: 18.9177. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 19.6677. Min Range: -19.6677

Max Act: 18.0427. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 19.6677. Min Range: -19.6677

Max Act: 16.9177. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 19.6677. Min Range: -19.6677

Max Act: 16.9177. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 19.6677. Min Range: -19.6677

Max Act: 15.7927. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 19.6677. Min Range: -19.6677

Max Act: 15.4177. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 19.6677. Min Range: -19.6677

Max Act: 15.2302. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 19.6677. Min Range: -19.6677

Max Act: 15.2302. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 19.6677. Min Range: -19.6677

Max Act: 14.4802. Min Act: -0.1700

Data Index: 1601652 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 19.6677. Min Range: -19.6677

Max Act: 14.3552. Min Act: -0.1700

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.9177. Min Act: -0.1700

Data Index: 1655744 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.7302. Min Act: -0.1700

Data Index: 1535151 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.5427. Min Act: -0.1700

Data Index: 1649474 (Python Code)

Max Activating Token Index: 807

Text #15

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.2927. Min Act: -0.1700

Data Index: 1548039 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.1677. Min Act: -0.1700

Data Index: 1556465 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 19.6677. Min Range: -19.6677

Max Act: 13.1677. Min Act: -0.1700

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 19.6677. Min Range: -19.6677

Max Act: 12.9802. Min Act: -0.1700

Data Index: 1529790 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 19.6677. Min Range: -19.6677

Max Act: 12.9177. Min Act: -0.1700

Data Index: 1597306 (Python Code)

Max Activating Token Index: 748