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

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

Neuron 2022 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: 4.0803. Min Range: -4.0803

Max Act: 4.0647. Min Act: -0.1700

Data Index: 903921 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 4.0803. Min Range: -4.0803

Max Act: 4.0490. Min Act: -0.1700

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 4.0803. Min Range: -4.0803

Max Act: 4.0803. Min Act: -0.1700

Data Index: 386593 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 4.0803. Min Range: -4.0803

Max Act: 4.0178. Min Act: -0.1700

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.9709. Min Act: -0.1700

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.9709. Min Act: -0.1700

Data Index: 900476 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.9083. Min Act: -0.1700

Data Index: 712177 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8458. Min Act: -0.1700

Data Index: 594485 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.9162. Min Act: -0.1700

Data Index: 518056 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8849. Min Act: -0.1700

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8536. Min Act: -0.1700

Data Index: 900802 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1290420 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8380. Min Act: -0.1700

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.8380. Min Act: -0.1700

Data Index: 1206767 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7754. Min Act: -0.1700

Data Index: 1358272 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7363. Min Act: -0.1700

Data Index: 1243613 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1249253 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7441. Min Act: -0.1700

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7911. Min Act: -0.1700

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 4.0803. Min Range: -4.0803

Max Act: 3.7911. Min Act: -0.1700

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 310