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

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

Neuron 1597 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.5856. Min Act: -0.1700

Data Index: 1038245 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.5230. Min Act: -0.1700

Data Index: 525549 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4917. Min Act: -0.1700

Data Index: 450960 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4917. Min Act: -0.1700

Data Index: 1030219 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 742610 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 899629 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 312985 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 34762 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3976. Min Act: -0.1700

Data Index: 1245018 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 175805 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4603. Min Act: -0.1700

Data Index: 713923 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3976. Min Act: -0.1700

Data Index: 779513 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3976. Min Act: -0.1700

Data Index: 867792 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3976. Min Act: -0.1700

Data Index: 209792 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.4290. Min Act: -0.1700

Data Index: 254436 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3976. Min Act: -0.1700

Data Index: 260602 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3662. Min Act: -0.1700

Data Index: 273466 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3662. Min Act: -0.1700

Data Index: 213360 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3662. Min Act: -0.1700

Data Index: 897593 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 3.5856. Min Range: -3.5856

Max Act: 3.3348. Min Act: -0.1700

Data Index: 915076 (C4 (Web Text))

Max Activating Token Index: 686