Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 161 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3619. Min Range: -3.3619

Max Act: 3.3619. Min Act: -0.1700

Data Index: 1284931 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 3.3619. Min Range: -3.3619

Max Act: 3.1103. Min Act: -0.1700

Data Index: 145573 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.3619. Min Range: -3.3619

Max Act: 3.0787. Min Act: -0.1700

Data Index: 880086 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9681. Min Act: -0.1700

Data Index: 811085 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9840. Min Act: -0.1700

Data Index: 598483 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9523. Min Act: -0.1700

Data Index: 797773 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9365. Min Act: -0.1700

Data Index: 678221 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9206. Min Act: -0.1700

Data Index: 1157691 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.9048. Min Act: -0.1700

Data Index: 159960 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8889. Min Act: -0.1700

Data Index: 809349 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8730. Min Act: -0.1700

Data Index: 428963 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8889. Min Act: -0.1700

Data Index: 639591 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8889. Min Act: -0.1700

Data Index: 844530 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8889. Min Act: -0.1700

Data Index: 665262 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8889. Min Act: -0.1700

Data Index: 418511 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8572. Min Act: -0.1700

Data Index: 472770 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8572. Min Act: -0.1700

Data Index: 665783 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8572. Min Act: -0.1700

Data Index: 383753 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8730. Min Act: -0.1700

Data Index: 1262203 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.3619. Min Range: -3.3619

Max Act: 2.8572. Min Act: -0.1700

Data Index: 451086 (C4 (Web Text))

Max Activating Token Index: 994