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

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

Neuron 1859 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5760. Min Act: -0.1700

Data Index: 1229663 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4820. Min Act: -0.1700

Data Index: 861172 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4663. Min Act: -0.1700

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4663. Min Act: -0.1700

Data Index: 569674 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4820. Min Act: -0.1700

Data Index: 935099 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5133. Min Act: -0.1700

Data Index: 1248708 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3722. Min Act: -0.1700

Data Index: 751795 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4507. Min Act: -0.1700

Data Index: 303282 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1358443 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4663. Min Act: -0.1700

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4350. Min Act: -0.1700

Data Index: 831159 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3565. Min Act: -0.1700

Data Index: 94670 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4036. Min Act: -0.1700

Data Index: 868547 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4350. Min Act: -0.1700

Data Index: 889140 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4036. Min Act: -0.1700

Data Index: 840065 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4663. Min Act: -0.1700

Data Index: 254057 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4350. Min Act: -0.1700

Data Index: 727574 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1174006 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4350. Min Act: -0.1700

Data Index: 86584 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4193. Min Act: -0.1700

Data Index: 728628 (C4 (Web Text))

Max Activating Token Index: 833