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

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

Neuron 2044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.7296. Min Act: -0.1700

Data Index: 218633 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 434249 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 612798 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.6044. Min Act: -0.1700

Data Index: 598544 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 220600 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.6044. Min Act: -0.1700

Data Index: 453062 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1320913 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 969991 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 739450 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1349315 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 523743 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 337200 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 800798 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1067124 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5104. Min Act: -0.1700

Data Index: 332306 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 1098610 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5417. Min Act: -0.1700

Data Index: 1184827 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5104. Min Act: -0.1700

Data Index: 383765 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5104. Min Act: -0.1700

Data Index: 625366 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 3.7296. Min Range: -3.7296

Max Act: 3.5104. Min Act: -0.1700

Data Index: 644890 (C4 (Web Text))

Max Activating Token Index: 269