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

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

Neuron 1391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.2554. Min Act: -0.1700

Data Index: 845567 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.2242. Min Act: -0.1700

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.2554. Min Act: -0.1700

Data Index: 143055 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1929. Min Act: -0.1700

Data Index: 753121 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1617. Min Act: -0.1700

Data Index: 314952 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0992. Min Act: -0.1700

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1617. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 339562 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 729955 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 204060 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0992. Min Act: -0.1700

Data Index: 98525 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 561204 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 153830 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0367. Min Act: -0.1700

Data Index: 771500 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.1304. Min Act: -0.1700

Data Index: 27328 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0992. Min Act: -0.1700

Data Index: 976871 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0679. Min Act: -0.1700

Data Index: 590021 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0992. Min Act: -0.1700

Data Index: 375567 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0367. Min Act: -0.1700

Data Index: 193303 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 7.2554. Min Range: -7.2554

Max Act: 7.0992. Min Act: -0.1700

Data Index: 518564 (C4 (Web Text))

Max Activating Token Index: 966