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

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

Neuron 608 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: 7.7110. Min Range: -7.7110

Max Act: 7.5860. Min Act: -0.1700

Data Index: 1257267 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.7110. Min Act: -0.1700

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.1485. Min Act: -0.1700

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.2735. Min Act: -0.1700

Data Index: 418730 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.0860. Min Act: -0.1700

Data Index: 365772 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.0860. Min Act: -0.1700

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.2110. Min Act: -0.1700

Data Index: 322657 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.0235. Min Act: -0.1700

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.1485. Min Act: -0.1700

Data Index: 1041514 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.8985. Min Act: -0.1700

Data Index: 983872 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.0235. Min Act: -0.1700

Data Index: 817899 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.9610. Min Act: -0.1700

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 7.7110. Min Range: -7.7110

Max Act: 7.0235. Min Act: -0.1700

Data Index: 798139 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.9610. Min Act: -0.1700

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.7735. Min Act: -0.1700

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.9610. Min Act: -0.1700

Data Index: 190283 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.7735. Min Act: -0.1700

Data Index: 64900 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.9610. Min Act: -0.1700

Data Index: 210387 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.8360. Min Act: -0.1700

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 7.7110. Min Range: -7.7110

Max Act: 6.8360. Min Act: -0.1700

Data Index: 704425 (C4 (Web Text))

Max Activating Token Index: 933