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

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

Neuron 1453 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: 5.1346. Min Range: -5.1346

Max Act: 5.1346. Min Act: -0.1700

Data Index: 1089230 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 5.1346. Min Range: -5.1346

Max Act: 5.0408. Min Act: -0.1700

Data Index: 768047 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.9783. Min Act: -0.1700

Data Index: 753597 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.9471. Min Act: -0.1700

Data Index: 908769 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.7908. Min Act: -0.1700

Data Index: 1090246 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.7283. Min Act: -0.1700

Data Index: 566033 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6971. Min Act: -0.1700

Data Index: 439344 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6971. Min Act: -0.1700

Data Index: 928450 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 1295394 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6658. Min Act: -0.1700

Data Index: 1059753 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 563273 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 1269677 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 160172 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 649853 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6346. Min Act: -0.1700

Data Index: 328669 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6033. Min Act: -0.1700

Data Index: 398066 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.5721. Min Act: -0.1700

Data Index: 615934 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6033. Min Act: -0.1700

Data Index: 696531 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6033. Min Act: -0.1700

Data Index: 1293001 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 5.1346. Min Range: -5.1346

Max Act: 4.6033. Min Act: -0.1700

Data Index: 337559 (C4 (Web Text))

Max Activating Token Index: 810