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

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

Neuron 850 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.6281. Min Act: -0.1700

Data Index: 411775 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5968. Min Act: -0.1700

Data Index: 243212 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5968. Min Act: -0.1700

Data Index: 1346844 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5343. Min Act: -0.1700

Data Index: 1232272 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5656. Min Act: -0.1700

Data Index: 874698 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 240845 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 1268948 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 112892 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5031. Min Act: -0.1700

Data Index: 122801 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5031. Min Act: -0.1700

Data Index: 938331 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.5031. Min Act: -0.1700

Data Index: 912930 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 87893 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 1105920 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 391133 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4093. Min Act: -0.1700

Data Index: 844412 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 897723 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4406. Min Act: -0.1700

Data Index: 836975 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4406. Min Act: -0.1700

Data Index: 395090 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4406. Min Act: -0.1700

Data Index: 418568 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 5.6281. Min Range: -5.6281

Max Act: 5.4718. Min Act: -0.1700

Data Index: 545480 (C4 (Web Text))

Max Activating Token Index: 227