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

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

Neuron 819 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.2323. Min Act: -0.1700

Data Index: 1149236 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1851. Min Act: -0.1700

Data Index: 1188922 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1693. Min Act: -0.1700

Data Index: 64670 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1378. Min Act: -0.1700

Data Index: 611568 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1221. Min Act: -0.1700

Data Index: 1186329 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0905. Min Act: -0.1700

Data Index: 1352766 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0748. Min Act: -0.1700

Data Index: 869632 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0748. Min Act: -0.1700

Data Index: 1165253 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0432. Min Act: -0.1700

Data Index: 670752 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0432. Min Act: -0.1700

Data Index: 626514 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0432. Min Act: -0.1700

Data Index: 795553 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0432. Min Act: -0.1700

Data Index: 1023492 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0590. Min Act: -0.1700

Data Index: 255289 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0274. Min Act: -0.1700

Data Index: 212229 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 3.2323. Min Range: -3.2323

Max Act: 2.9958. Min Act: -0.1700

Data Index: 566540 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0116. Min Act: -0.1700

Data Index: 99693 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0116. Min Act: -0.1700

Data Index: 512248 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0116. Min Act: -0.1700

Data Index: 721590 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0274. Min Act: -0.1700

Data Index: 957604 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0116. Min Act: -0.1700

Data Index: 20050 (C4 (Web Text))

Max Activating Token Index: 651