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

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

Neuron 1661 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1262353 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6425. Min Act: -0.1700

Data Index: 954589 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6582. Min Act: -0.1700

Data Index: 967976 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6895. Min Act: -0.1700

Data Index: 762780 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6895. Min Act: -0.1700

Data Index: 1341855 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1212544 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6738. Min Act: -0.1700

Data Index: 787053 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6112. Min Act: -0.1700

Data Index: 1206596 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1027337 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 1149846 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.5956. Min Act: -0.1700

Data Index: 700900 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1103388 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6895. Min Act: -0.1700

Data Index: 761319 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.5956. Min Act: -0.1700

Data Index: 1014967 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 899541 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 942123 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 109119 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6112. Min Act: -0.1700

Data Index: 977439 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 222996 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.6895. Min Range: -3.6895

Max Act: 3.6269. Min Act: -0.1700

Data Index: 111580 (C4 (Web Text))

Max Activating Token Index: 600