Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.8174. Min Act: -0.1700

Data Index: 1305761 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.6611. Min Act: -0.1700

Data Index: 707969 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.6611. Min Act: -0.1700

Data Index: 224874 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.6611. Min Act: -0.1700

Data Index: 1167872 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.5674. Min Act: -0.1700

Data Index: 1351155 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.5049. Min Act: -0.1700

Data Index: 180213 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.5361. Min Act: -0.1700

Data Index: 314817 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.4424. Min Act: -0.1700

Data Index: 373570 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.4424. Min Act: -0.1700

Data Index: 366445 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.4424. Min Act: -0.1700

Data Index: 107941 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3799. Min Act: -0.1700

Data Index: 703208 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.4111. Min Act: -0.1699

Data Index: 523189 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3799. Min Act: -0.1700

Data Index: 583987 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3486. Min Act: -0.1699

Data Index: 602823 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3486. Min Act: -0.1699

Data Index: 231739 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3486. Min Act: -0.1700

Data Index: 7670 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3174. Min Act: -0.1700

Data Index: 688717 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.3174. Min Act: -0.1700

Data Index: 102893 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.2549. Min Act: -0.1700

Data Index: 874264 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 5.8174. Min Range: -5.8174

Max Act: 5.2861. Min Act: -0.1700

Data Index: 976405 (C4 (Web Text))

Max Activating Token Index: 550