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

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

Neuron 58 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: 3.1891. Min Range: -3.1891

Max Act: 3.1891. Min Act: -0.1700

Data Index: 122076 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.1733. Min Act: -0.1700

Data Index: 882896 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.1891. Min Act: -0.1700

Data Index: 986081 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.1576. Min Act: -0.1700

Data Index: 794800 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0946. Min Act: -0.1700

Data Index: 1331759 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 947705 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 636273 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0788. Min Act: -0.1700

Data Index: 91891 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0630. Min Act: -0.1700

Data Index: 746432 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0630. Min Act: -0.1700

Data Index: 1116318 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1064619 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0314. Min Act: -0.1700

Data Index: 609434 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 561536 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 410818 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.1891. Min Range: -3.1891

Max Act: 3.0156. Min Act: -0.1700

Data Index: 682235 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9840. Min Act: -0.1700

Data Index: 1173846 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9840. Min Act: -0.1700

Data Index: 463839 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 1253149 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9998. Min Act: -0.1700

Data Index: 133724 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 3.1891. Min Range: -3.1891

Max Act: 2.9840. Min Act: -0.1700

Data Index: 538169 (C4 (Web Text))

Max Activating Token Index: 522