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

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

Neuron 346 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: 5.8218. Min Range: -5.8218

Max Act: 5.8218. Min Act: -0.1699

Data Index: 111938 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5093. Min Act: -0.1700

Data Index: 1126825 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5406. Min Act: -0.1700

Data Index: 8971 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5093. Min Act: -0.1700

Data Index: 940992 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.5093. Min Act: -0.1699

Data Index: 495139 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.4781. Min Act: -0.1700

Data Index: 1162460 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.4156. Min Act: -0.1700

Data Index: 12467 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.4156. Min Act: -0.1700

Data Index: 403943 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.4156. Min Act: -0.1700

Data Index: 326210 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.3843. Min Act: -0.1699

Data Index: 961441 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.3218. Min Act: -0.1700

Data Index: 1206524 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.3531. Min Act: -0.1700

Data Index: 1040645 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.3531. Min Act: -0.1700

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2593. Min Act: -0.1700

Data Index: 468445 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2906. Min Act: -0.1700

Data Index: 1014291 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2593. Min Act: -0.1700

Data Index: 638161 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2906. Min Act: -0.1700

Data Index: 930905 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2906. Min Act: -0.1700

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2906. Min Act: -0.1700

Data Index: 486747 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 5.8218. Min Range: -5.8218

Max Act: 5.2906. Min Act: -0.1700

Data Index: 1055007 (C4 (Web Text))

Max Activating Token Index: 460