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

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

Neuron 306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.9121. Min Act: -0.1700

Data Index: 500253 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7401. Min Act: -0.1700

Data Index: 570770 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7401. Min Act: -0.1700

Data Index: 403835 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7244. Min Act: -0.1700

Data Index: 858352 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7088. Min Act: -0.1700

Data Index: 1268589 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7401. Min Act: -0.1700

Data Index: 1075931 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6931. Min Act: -0.1700

Data Index: 221776 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7088. Min Act: -0.1700

Data Index: 1357155 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6931. Min Act: -0.1700

Data Index: 787425 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6618. Min Act: -0.1700

Data Index: 152525 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6618. Min Act: -0.1700

Data Index: 259655 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6618. Min Act: -0.1700

Data Index: 5172 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6305. Min Act: -0.1700

Data Index: 165346 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6618. Min Act: -0.1700

Data Index: 799370 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6462. Min Act: -0.1700

Data Index: 739093 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6462. Min Act: -0.1700

Data Index: 1062633 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6462. Min Act: -0.1700

Data Index: 447359 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6618. Min Act: -0.1700

Data Index: 865126 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6305. Min Act: -0.1700

Data Index: 939698 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.6149. Min Act: -0.1700

Data Index: 710305 (C4 (Web Text))

Max Activating Token Index: 920