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

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

Neuron 1867 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: 3.3985. Min Range: -3.3985

Max Act: 3.3985. Min Act: -0.1700

Data Index: 240624 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3514. Min Act: -0.1700

Data Index: 640238 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3514. Min Act: -0.1700

Data Index: 1294890 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3357. Min Act: -0.1700

Data Index: 121090 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3357. Min Act: -0.1700

Data Index: 726909 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3200. Min Act: -0.1700

Data Index: 506283 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2886. Min Act: -0.1700

Data Index: 196382 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.3043. Min Act: -0.1700

Data Index: 238496 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 338237 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 70887 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 240215 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 100536 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 690810 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2729. Min Act: -0.1700

Data Index: 1106512 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2572. Min Act: -0.1700

Data Index: 30600 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2258. Min Act: -0.1700

Data Index: 1033820 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2415. Min Act: -0.1700

Data Index: 777426 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2100. Min Act: -0.1700

Data Index: 462268 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2258. Min Act: -0.1700

Data Index: 663719 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 3.3985. Min Range: -3.3985

Max Act: 3.2415. Min Act: -0.1700

Data Index: 954080 (C4 (Web Text))

Max Activating Token Index: 779