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

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

Neuron 1906 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: 14.2255. Min Range: -14.2255

Max Act: 14.2255. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 14.2255. Min Range: -14.2255

Max Act: 14.1005. Min Act: -0.1699

Data Index: 1483328 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 14.2255. Min Range: -14.2255

Max Act: 13.9130. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 14.2255. Min Range: -14.2255

Max Act: 13.0380. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 14.2255. Min Range: -14.2255

Max Act: 12.8505. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 14.2255. Min Range: -14.2255

Max Act: 12.2255. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 14.2255. Min Range: -14.2255

Max Act: 11.8505. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 14.2255. Min Range: -14.2255

Max Act: 11.6630. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.9130. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 649

Text #9

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.8505. Min Act: -0.1700

Data Index: 1655744 (Python Code)

Max Activating Token Index: 328

Text #10

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.7880. Min Act: -0.1699

Data Index: 1641948 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.6005. Min Act: -0.1699

Data Index: 1601652 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.4130. Min Act: -0.1699

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.3505. Min Act: -0.1700

Data Index: 1535151 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 14.2255. Min Range: -14.2255

Max Act: 10.1630. Min Act: -0.1700

Data Index: 1597306 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 14.2255. Min Range: -14.2255

Max Act: 9.9755. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 14.2255. Min Range: -14.2255

Max Act: 9.9130. Min Act: -0.1700

Data Index: 1652188 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 14.2255. Min Range: -14.2255

Max Act: 9.7880. Min Act: -0.1700

Data Index: 1556465 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 14.2255. Min Range: -14.2255

Max Act: 9.7880. Min Act: -0.1700

Data Index: 1649474 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 14.2255. Min Range: -14.2255

Max Act: 9.7255. Min Act: -0.1700

Data Index: 1548039 (Python Code)

Max Activating Token Index: 28