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

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

Neuron 925 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: 3.2848. Min Range: -3.2848

Max Act: 3.2848. Min Act: -0.1700

Data Index: 542067 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.2219. Min Act: -0.1700

Data Index: 639303 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.2534. Min Act: -0.1700

Data Index: 86451 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 887340 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1905. Min Act: -0.1700

Data Index: 343801 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1905. Min Act: -0.1700

Data Index: 763287 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 147251 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 540452 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1905. Min Act: -0.1700

Data Index: 603204 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1905. Min Act: -0.1700

Data Index: 738522 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1137745 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1275. Min Act: -0.1700

Data Index: 241310 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 905017 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 127789 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 703921 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1080031 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 90760 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 1123687 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1590. Min Act: -0.1700

Data Index: 1071018 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.2848. Min Range: -3.2848

Max Act: 3.1275. Min Act: -0.1700

Data Index: 160020 (C4 (Web Text))

Max Activating Token Index: 404