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

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

Neuron 1298 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.3214. Min Act: -0.1700

Data Index: 1504179 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.3214. Min Act: -0.1700

Data Index: 1617701 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.1339. Min Act: -0.1700

Data Index: 1399775 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.1651. Min Act: -0.1700

Data Index: 1497273 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.1026. Min Act: -0.1700

Data Index: 1435256 (Python Code)

Max Activating Token Index: 422

Text #5

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.0089. Min Act: -0.1700

Data Index: 1624860 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.0089. Min Act: -0.1700

Data Index: 1477380 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.0089. Min Act: -0.1700

Data Index: 1528753 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.9151. Min Act: -0.1700

Data Index: 379527 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8526. Min Act: -0.1700

Data Index: 583512 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 8.3214. Min Range: -8.3214

Max Act: 8.0089. Min Act: -0.1700

Data Index: 1598588 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.9776. Min Act: -0.1700

Data Index: 1375164 (Python Code)

Max Activating Token Index: 799

Text #12

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8526. Min Act: -0.1700

Data Index: 1414992 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.9151. Min Act: -0.1700

Data Index: 1651011 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.9464. Min Act: -0.1700

Data Index: 1645980 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8839. Min Act: -0.1700

Data Index: 1625621 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8839. Min Act: -0.1700

Data Index: 1362729 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8526. Min Act: -0.1700

Data Index: 1481206 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.9151. Min Act: -0.1700

Data Index: 1421085 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 8.3214. Min Range: -8.3214

Max Act: 7.8526. Min Act: -0.1700

Data Index: 1424735 (Python Code)

Max Activating Token Index: 66