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

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

Neuron 912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.4811. Min Act: -0.1700

Data Index: 153802 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.1686. Min Act: -0.1700

Data Index: 10119 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1357110 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1216659 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.0748. Min Act: -0.1700

Data Index: 522789 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 25870 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 5342 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 846833 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.0436. Min Act: -0.1699

Data Index: 423715 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 546979 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 760355 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 5.4811. Min Range: -5.4811

Max Act: 5.0123. Min Act: -0.1700

Data Index: 86614 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 115521 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.8873. Min Act: -0.1700

Data Index: 1261254 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9498. Min Act: -0.1700

Data Index: 364861 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9498. Min Act: -0.1700

Data Index: 1193166 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.8873. Min Act: -0.1700

Data Index: 624149 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.9498. Min Act: -0.1700

Data Index: 340580 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.8873. Min Act: -0.1700

Data Index: 834141 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 5.4811. Min Range: -5.4811

Max Act: 4.8873. Min Act: -0.1700

Data Index: 418805 (C4 (Web Text))

Max Activating Token Index: 732