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

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

Neuron 1139 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: 7.4734. Min Range: -7.4734

Max Act: 7.3796. Min Act: -0.1698

Data Index: 979343 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.4734. Min Act: -0.1698

Data Index: 645722 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.3171. Min Act: -0.1700

Data Index: 842694 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.2234. Min Act: -0.1700

Data Index: 100843 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0984. Min Act: -0.1700

Data Index: 350584 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0671. Min Act: -0.1700

Data Index: 296975 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.1609. Min Act: -0.1700

Data Index: 1010442 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0359. Min Act: -0.1700

Data Index: 132764 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0984. Min Act: -0.1699

Data Index: 795132 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0671. Min Act: -0.1700

Data Index: 716450 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0984. Min Act: -0.1699

Data Index: 70048 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0046. Min Act: -0.1700

Data Index: 1162210 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0046. Min Act: -0.1700

Data Index: 131112 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0671. Min Act: -0.1700

Data Index: 378954 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0671. Min Act: -0.1700

Data Index: 628423 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 7.4734. Min Range: -7.4734

Max Act: 6.9109. Min Act: -0.1700

Data Index: 525415 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 7.4734. Min Range: -7.4734

Max Act: 6.9421. Min Act: -0.1700

Data Index: 970941 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0359. Min Act: -0.1700

Data Index: 511404 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0046. Min Act: -0.1700

Data Index: 1332500 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 7.4734. Min Range: -7.4734

Max Act: 7.0046. Min Act: -0.1700

Data Index: 295648 (C4 (Web Text))

Max Activating Token Index: 843