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

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

Neuron 1652 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: 7.9342. Min Range: -7.9342

Max Act: 7.9342. Min Act: -0.1700

Data Index: 139595 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.7467. Min Act: -0.1700

Data Index: 863863 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.8092. Min Act: -0.1700

Data Index: 230048 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.7467. Min Act: -0.1700

Data Index: 799489 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.5592. Min Act: -0.1700

Data Index: 1523406 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.6217. Min Act: -0.1700

Data Index: 1200676 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.6217. Min Act: -0.1700

Data Index: 1191686 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.6217. Min Act: -0.1699

Data Index: 1256526 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.5592. Min Act: -0.1700

Data Index: 1117966 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4342. Min Act: -0.1700

Data Index: 1305566 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4967. Min Act: -0.1700

Data Index: 307703 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4967. Min Act: -0.1700

Data Index: 298252 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4967. Min Act: -0.1700

Data Index: 284581 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4967. Min Act: -0.1700

Data Index: 1173837 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4967. Min Act: -0.1700

Data Index: 1523363 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4342. Min Act: -0.1700

Data Index: 1518240 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.3717. Min Act: -0.1700

Data Index: 1636524 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4342. Min Act: -0.1700

Data Index: 1114345 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.4342. Min Act: -0.1700

Data Index: 521116 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 7.9342. Min Range: -7.9342

Max Act: 7.3717. Min Act: -0.1700

Data Index: 1229349 (C4 (Web Text))

Max Activating Token Index: 313