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

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

Neuron 685 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: 5.8077. Min Range: -5.8077

Max Act: 5.8077. Min Act: -0.1700

Data Index: 1099072 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6827. Min Act: -0.1700

Data Index: 409200 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6514. Min Act: -0.1700

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6827. Min Act: -0.1700

Data Index: 132494 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6514. Min Act: -0.1700

Data Index: 642866 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6514. Min Act: -0.1700

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 842480 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 605186 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6202. Min Act: -0.1700

Data Index: 583607 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.6202. Min Act: -0.1700

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5264. Min Act: -0.1700

Data Index: 940742 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5577. Min Act: -0.1700

Data Index: 1187589 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1260580 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5264. Min Act: -0.1700

Data Index: 786409 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5264. Min Act: -0.1700

Data Index: 295300 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 497182 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.5889. Min Act: -0.1700

Data Index: 943595 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 5.8077. Min Range: -5.8077

Max Act: 5.4952. Min Act: -0.1700

Data Index: 909430 (C4 (Web Text))

Max Activating Token Index: 387