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

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

Neuron 1088 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: 7.0806. Min Range: -7.0806

Max Act: 7.0806. Min Act: -0.1700

Data Index: 793755 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.9244. Min Act: -0.1700

Data Index: 1026705 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.9244. Min Act: -0.1700

Data Index: 1232169 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7681. Min Act: -0.1700

Data Index: 933308 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.8306. Min Act: -0.1700

Data Index: 97242 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.9244. Min Act: -0.1700

Data Index: 941538 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.9244. Min Act: -0.1700

Data Index: 864041 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.8931. Min Act: -0.1700

Data Index: 928066 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7994. Min Act: -0.1700

Data Index: 293679 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.8619. Min Act: -0.1700

Data Index: 1311155 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.8306. Min Act: -0.1700

Data Index: 1154319 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7994. Min Act: -0.1700

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7994. Min Act: -0.1700

Data Index: 207490 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.8306. Min Act: -0.1700

Data Index: 27180 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7056. Min Act: -0.1700

Data Index: 825934 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.6431. Min Act: -0.1700

Data Index: 604584 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7369. Min Act: -0.1700

Data Index: 1070900 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7056. Min Act: -0.1700

Data Index: 677404 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7056. Min Act: -0.1700

Data Index: 1152570 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 7.0806. Min Range: -7.0806

Max Act: 6.7681. Min Act: -0.1700

Data Index: 408095 (C4 (Web Text))

Max Activating Token Index: 383