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

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

Neuron 327 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: 3.3388. Min Range: -3.3388

Max Act: 3.3388. Min Act: -0.1700

Data Index: 1240448 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.3231. Min Act: -0.1700

Data Index: 1310022 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.3074. Min Act: -0.1700

Data Index: 527025 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2759. Min Act: -0.1700

Data Index: 245765 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2759. Min Act: -0.1700

Data Index: 125724 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2602. Min Act: -0.1700

Data Index: 263388 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2602. Min Act: -0.1700

Data Index: 650149 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2759. Min Act: -0.1700

Data Index: 475156 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2602. Min Act: -0.1700

Data Index: 1038620 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2288. Min Act: -0.1700

Data Index: 239675 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2288. Min Act: -0.1700

Data Index: 1293317 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2131. Min Act: -0.1700

Data Index: 280311 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2288. Min Act: -0.1700

Data Index: 63117 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2131. Min Act: -0.1700

Data Index: 1347895 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.2131. Min Act: -0.1700

Data Index: 481854 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.1816. Min Act: -0.1700

Data Index: 551660 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.1973. Min Act: -0.1700

Data Index: 1193131 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.1816. Min Act: -0.1700

Data Index: 264590 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.1816. Min Act: -0.1700

Data Index: 553013 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.3388. Min Range: -3.3388

Max Act: 3.1816. Min Act: -0.1700

Data Index: 792414 (C4 (Web Text))

Max Activating Token Index: 415