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

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

Neuron 1927 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: 8.0368. Min Range: -8.0368

Max Act: 8.0368. Min Act: -0.1700

Data Index: 1333086 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.9118. Min Act: -0.1700

Data Index: 351424 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.7243. Min Act: -0.1700

Data Index: 647448 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.7243. Min Act: -0.1700

Data Index: 384632 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.7243. Min Act: -0.1700

Data Index: 699239 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.7243. Min Act: -0.1700

Data Index: 819675 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.7243. Min Act: -0.1700

Data Index: 911832 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.4118. Min Act: -0.1700

Data Index: 261246 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.5368. Min Act: -0.1700

Data Index: 479436 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.2868. Min Act: -0.1700

Data Index: 1057739 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.2243. Min Act: -0.1700

Data Index: 1265499 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.2243. Min Act: -0.1700

Data Index: 1305859 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.1618. Min Act: -0.1700

Data Index: 218908 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.2243. Min Act: -0.1700

Data Index: 454089 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.0993. Min Act: -0.1700

Data Index: 659506 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.0993. Min Act: -0.1700

Data Index: 1350176 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.1618. Min Act: -0.1700

Data Index: 859959 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.0993. Min Act: -0.1700

Data Index: 1335959 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.1618. Min Act: -0.1700

Data Index: 49664 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 8.0368. Min Range: -8.0368

Max Act: 7.0368. Min Act: -0.1700

Data Index: 645664 (C4 (Web Text))

Max Activating Token Index: 708