Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.4791. Min Range: -8.4791

Max Act: 8.2916. Min Act: -0.1700

Data Index: 650898 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 8.4791. Min Range: -8.4791

Max Act: 8.4791. Min Act: -0.1700

Data Index: 13333 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 8.4791. Min Range: -8.4791

Max Act: 8.1041. Min Act: -0.1700

Data Index: 456534 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.7916. Min Act: -0.1699

Data Index: 761266 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6666. Min Act: -0.1700

Data Index: 1164498 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6041. Min Act: -0.1699

Data Index: 1084848 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6041. Min Act: -0.1700

Data Index: 587177 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6666. Min Act: -0.1700

Data Index: 707681 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.9166. Min Act: -0.1700

Data Index: 465290 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.5416. Min Act: -0.1699

Data Index: 1255461 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.3541. Min Act: -0.1700

Data Index: 1264507 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6041. Min Act: -0.1699

Data Index: 747607 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.5416. Min Act: -0.1700

Data Index: 1032542 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.4166. Min Act: -0.1699

Data Index: 211382 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.6041. Min Act: -0.1700

Data Index: 1174012 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.5416. Min Act: -0.1700

Data Index: 170962 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.4166. Min Act: -0.1700

Data Index: 43972 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.4791. Min Act: -0.1699

Data Index: 567713 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.4166. Min Act: -0.1699

Data Index: 299374 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 8.4791. Min Range: -8.4791

Max Act: 7.5416. Min Act: -0.1700

Data Index: 335505 (C4 (Web Text))

Max Activating Token Index: 705