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

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

Neuron 376 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4778. Min Act: -0.1700

Data Index: 955990 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4621. Min Act: -0.1700

Data Index: 1072964 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4151. Min Act: -0.1700

Data Index: 950301 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4308. Min Act: -0.1700

Data Index: 379735 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4308. Min Act: -0.1700

Data Index: 484917 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.4151. Min Act: -0.1700

Data Index: 864016 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3837. Min Act: -0.1700

Data Index: 837327 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3837. Min Act: -0.1700

Data Index: 907010 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3367. Min Act: -0.1700

Data Index: 556990 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3524. Min Act: -0.1700

Data Index: 680512 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1258646 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3524. Min Act: -0.1700

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3524. Min Act: -0.1700

Data Index: 258674 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3367. Min Act: -0.1700

Data Index: 1199954 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3210. Min Act: -0.1700

Data Index: 378067 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1107971 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3210. Min Act: -0.1700

Data Index: 72846 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.3053. Min Act: -0.1700

Data Index: 282752 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.2738. Min Act: -0.1700

Data Index: 724337 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 3.4778. Min Range: -3.4778

Max Act: 3.2896. Min Act: -0.1700

Data Index: 783633 (C4 (Web Text))

Max Activating Token Index: 332