Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 328 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.7638. Min Act: -0.1700

Data Index: 976923 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.7638. Min Act: -0.1700

Data Index: 239674 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6856. Min Act: -0.1700

Data Index: 403240 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6543. Min Act: -0.1700

Data Index: 80095 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6230. Min Act: -0.1700

Data Index: 1287097 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6386. Min Act: -0.1700

Data Index: 597001 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6386. Min Act: -0.1700

Data Index: 338365 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6386. Min Act: -0.1700

Data Index: 848918 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6543. Min Act: -0.1700

Data Index: 682742 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5447. Min Act: -0.1700

Data Index: 350756 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6073. Min Act: -0.1700

Data Index: 46209 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5917. Min Act: -0.1700

Data Index: 673816 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5604. Min Act: -0.1700

Data Index: 63630 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5917. Min Act: -0.1700

Data Index: 988457 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5760. Min Act: -0.1700

Data Index: 737740 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5760. Min Act: -0.1700

Data Index: 774041 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5760. Min Act: -0.1700

Data Index: 1052662 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6073. Min Act: -0.1700

Data Index: 638728 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.6386. Min Act: -0.1700

Data Index: 15212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.7638. Min Range: -3.7638

Max Act: 3.5760. Min Act: -0.1700

Data Index: 1265072 (C4 (Web Text))

Max Activating Token Index: 251