Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1560 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9391. Min Act: -0.1699

Data Index: 730196 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9127. Min Act: -0.1700

Data Index: 41300 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6390. Min Act: -0.1700

Data Index: 251506 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6397. Min Act: -0.1691

Data Index: 1044153 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5887. Min Act: -0.1653

Data Index: 1619214 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5717. Min Act: -0.1699

Data Index: 1373367 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6089. Min Act: -0.1700

Data Index: 1016857 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5982. Min Act: -0.1693

Data Index: 97335 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5837. Min Act: -0.1699

Data Index: 110099 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5528. Min Act: -0.1700

Data Index: 974769 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1128937 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5779. Min Act: -0.1700

Data Index: 1144208 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5682. Min Act: -0.1699

Data Index: 371287 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1393527 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.5316. Min Act: -0.1700

Data Index: 1626473 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4884. Min Act: -0.1699

Data Index: 55113 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4907. Min Act: -0.1659

Data Index: 246538 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4888. Min Act: -0.1698

Data Index: 714448 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4870. Min Act: -0.1699

Data Index: 1363878 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.4694. Min Act: -0.1699

Data Index: 83027 (C4 (Web Text))

Max Activating Token Index: 924