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

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

Neuron 1011 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: 3.3496. Min Range: -3.3496

Max Act: 3.3496. Min Act: -0.1700

Data Index: 1213171 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2397. Min Act: -0.1700

Data Index: 591056 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1140395 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2397. Min Act: -0.1700

Data Index: 835701 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2239. Min Act: -0.1700

Data Index: 1082245 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2239. Min Act: -0.1700

Data Index: 1282221 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.2082. Min Act: -0.1700

Data Index: 91763 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1767. Min Act: -0.1700

Data Index: 728255 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1767. Min Act: -0.1700

Data Index: 576500 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1767. Min Act: -0.1700

Data Index: 1227377 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1452. Min Act: -0.1700

Data Index: 671510 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1295. Min Act: -0.1700

Data Index: 918017 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1767. Min Act: -0.1700

Data Index: 947929 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1610. Min Act: -0.1700

Data Index: 1092149 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1610. Min Act: -0.1700

Data Index: 443201 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1295. Min Act: -0.1700

Data Index: 222881 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1295. Min Act: -0.1700

Data Index: 754181 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1610. Min Act: -0.1700

Data Index: 759208 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1610. Min Act: -0.1700

Data Index: 896381 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 3.3496. Min Range: -3.3496

Max Act: 3.1137. Min Act: -0.1700

Data Index: 498570 (C4 (Web Text))

Max Activating Token Index: 654