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

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

Neuron 391 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: 5.1120. Min Range: -5.1120

Max Act: 5.1120. Min Act: -0.1699

Data Index: 46360 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 5.1120. Min Range: -5.1120

Max Act: 5.1120. Min Act: -0.1700

Data Index: 1244613 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.9870. Min Act: -0.1700

Data Index: 721477 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.9557. Min Act: -0.1700

Data Index: 494365 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8932. Min Act: -0.1700

Data Index: 838574 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8620. Min Act: -0.1700

Data Index: 51148 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8307. Min Act: -0.1700

Data Index: 751612 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8307. Min Act: -0.1700

Data Index: 758564 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.8307. Min Act: -0.1700

Data Index: 638708 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7995. Min Act: -0.1700

Data Index: 981472 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7370. Min Act: -0.1700

Data Index: 909854 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7682. Min Act: -0.1700

Data Index: 549898 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7995. Min Act: -0.1700

Data Index: 866720 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7682. Min Act: -0.1700

Data Index: 906360 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7057. Min Act: -0.1700

Data Index: 628979 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.6745. Min Act: -0.1700

Data Index: 69178 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.6745. Min Act: -0.1700

Data Index: 1157531 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7057. Min Act: -0.1700

Data Index: 583814 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.7057. Min Act: -0.1700

Data Index: 922768 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 5.1120. Min Range: -5.1120

Max Act: 4.6432. Min Act: -0.1700

Data Index: 215905 (C4 (Web Text))

Max Activating Token Index: 905