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

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

Neuron 1033 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.7496. Min Act: -0.1700

Data Index: 131394 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.6557. Min Act: -0.1700

Data Index: 345324 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.6244. Min Act: -0.1700

Data Index: 411807 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.6244. Min Act: -0.1700

Data Index: 356267 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5931. Min Act: -0.1700

Data Index: 582126 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5931. Min Act: -0.1700

Data Index: 1330110 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5617. Min Act: -0.1700

Data Index: 985367 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5617. Min Act: -0.1700

Data Index: 1281611 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5617. Min Act: -0.1700

Data Index: 1206402 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5617. Min Act: -0.1700

Data Index: 1084746 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5304. Min Act: -0.1700

Data Index: 500365 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.4991. Min Act: -0.1700

Data Index: 106930 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5304. Min Act: -0.1700

Data Index: 120388 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5617. Min Act: -0.1700

Data Index: 612823 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5304. Min Act: -0.1700

Data Index: 849292 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.5304. Min Act: -0.1700

Data Index: 525400 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.4677. Min Act: -0.1700

Data Index: 707931 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.4364. Min Act: -0.1700

Data Index: 307823 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.4991. Min Act: -0.1700

Data Index: 1000399 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 3.7496. Min Range: -3.7496

Max Act: 3.4677. Min Act: -0.1700

Data Index: 506311 (C4 (Web Text))

Max Activating Token Index: 822