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

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

Neuron 339 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: 5.5827. Min Range: -5.5827

Max Act: 5.5827. Min Act: -0.1700

Data Index: 873146 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5202. Min Act: -0.1700

Data Index: 396107 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3952. Min Act: -0.1700

Data Index: 1032926 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4577. Min Act: -0.1700

Data Index: 653936 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3640. Min Act: -0.1700

Data Index: 714504 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3952. Min Act: -0.1700

Data Index: 955104 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2390. Min Act: -0.1700

Data Index: 835127 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3640. Min Act: -0.1700

Data Index: 1331563 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3952. Min Act: -0.1700

Data Index: 1218281 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2702. Min Act: -0.1700

Data Index: 188904 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.3015. Min Act: -0.1700

Data Index: 1228257 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2390. Min Act: -0.1700

Data Index: 624403 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.1452. Min Act: -0.1700

Data Index: 201795 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.1765. Min Act: -0.1700

Data Index: 350802 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2702. Min Act: -0.1700

Data Index: 738006 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2077. Min Act: -0.1700

Data Index: 834501 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.1140. Min Act: -0.1700

Data Index: 1068843 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.1452. Min Act: -0.1700

Data Index: 439289 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2390. Min Act: -0.1700

Data Index: 941828 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.2390. Min Act: -0.1700

Data Index: 823052 (C4 (Web Text))

Max Activating Token Index: 417