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

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

Neuron 1965 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: 5.9963. Min Range: -5.9963

Max Act: 5.9963. Min Act: -0.1700

Data Index: 991235 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.9651. Min Act: -0.1700

Data Index: 129437 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.9963. Min Act: -0.1700

Data Index: 1325101 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.9338. Min Act: -0.1700

Data Index: 725699 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.8713. Min Act: -0.1700

Data Index: 1283170 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.9338. Min Act: -0.1700

Data Index: 902071 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.8088. Min Act: -0.1700

Data Index: 548459 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7463. Min Act: -0.1700

Data Index: 647867 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7776. Min Act: -0.1700

Data Index: 171701 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7463. Min Act: -0.1700

Data Index: 841565 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7151. Min Act: -0.1700

Data Index: 191616 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7151. Min Act: -0.1700

Data Index: 282990 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7151. Min Act: -0.1700

Data Index: 194478 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7151. Min Act: -0.1700

Data Index: 602456 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.6838. Min Act: -0.1700

Data Index: 565899 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.7151. Min Act: -0.1700

Data Index: 42306 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.6213. Min Act: -0.1700

Data Index: 226220 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.6526. Min Act: -0.1700

Data Index: 649242 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.6838. Min Act: -0.1700

Data Index: 897098 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 5.9963. Min Range: -5.9963

Max Act: 5.6526. Min Act: -0.1700

Data Index: 469387 (C4 (Web Text))

Max Activating Token Index: 8