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

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

Neuron 328 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: 5.2621. Min Range: -5.2621

Max Act: 5.2308. Min Act: -0.1700

Data Index: 773181 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.2621. Min Act: -0.1700

Data Index: 926429 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1683. Min Act: -0.1700

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1996. Min Act: -0.1700

Data Index: 1155728 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1996. Min Act: -0.1700

Data Index: 1274037 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1371. Min Act: -0.1700

Data Index: 837763 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1683. Min Act: -0.1700

Data Index: 436844 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1371. Min Act: -0.1700

Data Index: 264871 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0746. Min Act: -0.1700

Data Index: 627216 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.2621. Min Act: -0.1700

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1058. Min Act: -0.1700

Data Index: 960449 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0746. Min Act: -0.1700

Data Index: 581616 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0121. Min Act: -0.1700

Data Index: 858738 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.1058. Min Act: -0.1700

Data Index: 614939 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0746. Min Act: -0.1700

Data Index: 725402 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1235928 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 5.2621. Min Range: -5.2621

Max Act: 5.0121. Min Act: -0.1700

Data Index: 431464 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 5.2621. Min Range: -5.2621

Max Act: 4.9183. Min Act: -0.1700

Data Index: 113387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.2621. Min Range: -5.2621

Max Act: 4.8871. Min Act: -0.1700

Data Index: 1045313 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 5.2621. Min Range: -5.2621

Max Act: 4.9183. Min Act: -0.1700

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 827