Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1110 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.2313. Min Act: -0.1700

Data Index: 566163 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1054. Min Act: -0.1700

Data Index: 333973 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1211. Min Act: -0.1700

Data Index: 169744 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1054. Min Act: -0.1700

Data Index: 1158439 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.1211. Min Act: -0.1700

Data Index: 141148 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0896. Min Act: -0.1700

Data Index: 601966 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0896. Min Act: -0.1700

Data Index: 707811 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1241907 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0580. Min Act: -0.1700

Data Index: 553056 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0423. Min Act: -0.1700

Data Index: 719132 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1212898 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0423. Min Act: -0.1700

Data Index: 1319936 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0423. Min Act: -0.1700

Data Index: 1300337 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1123367 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0423. Min Act: -0.1700

Data Index: 586799 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0265. Min Act: -0.1700

Data Index: 364406 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0580. Min Act: -0.1700

Data Index: 192791 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0265. Min Act: -0.1700

Data Index: 197935 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1276258 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.2313. Min Range: -3.2313

Max Act: 3.0265. Min Act: -0.1700

Data Index: 766458 (C4 (Web Text))

Max Activating Token Index: 386