Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 475 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.0361. Min Range: -7.0361

Max Act: 7.0361. Min Act: -0.1700

Data Index: 800377 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.8173. Min Act: -0.1700

Data Index: 954157 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.7861. Min Act: -0.1700

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.8173. Min Act: -0.1700

Data Index: 890208 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.6611. Min Act: -0.1700

Data Index: 47631 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.5361. Min Act: -0.1700

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.5361. Min Act: -0.1700

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.5673. Min Act: -0.1700

Data Index: 1049083 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.5048. Min Act: -0.1700

Data Index: 786036 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.5048. Min Act: -0.1700

Data Index: 872282 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.4736. Min Act: -0.1700

Data Index: 392871 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.4423. Min Act: -0.1700

Data Index: 1203409 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.4423. Min Act: -0.1700

Data Index: 1116178 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.3798. Min Act: -0.1700

Data Index: 1053474 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.4111. Min Act: -0.1700

Data Index: 594640 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.4736. Min Act: -0.1700

Data Index: 86478 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.3798. Min Act: -0.1700

Data Index: 977292 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.3486. Min Act: -0.1700

Data Index: 1244015 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.3486. Min Act: -0.1700

Data Index: 622526 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 7.0361. Min Range: -7.0361

Max Act: 6.3798. Min Act: -0.1700

Data Index: 316198 (C4 (Web Text))

Max Activating Token Index: 365