Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 865 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.7722. Min Act: -0.1700

Data Index: 4524278 (Open Web Text)

Max Activating Token Index: 117

Text #1

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6625. Min Act: -0.1700

Data Index: 7986532 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6454. Min Act: -0.1700

Data Index: 1334014 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6042. Min Act: -0.1700

Data Index: 8208451 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6299. Min Act: -0.1700

Data Index: 7325057 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6459. Min Act: -0.1700

Data Index: 7374315 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5904. Min Act: -0.1700

Data Index: 823697 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6005. Min Act: -0.1700

Data Index: 8368661 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5887. Min Act: -0.1700

Data Index: 4327103 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.6113. Min Act: -0.1700

Data Index: 1831140 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5780. Min Act: -0.1700

Data Index: 8123305 (Open Web Text)

Max Activating Token Index: 489

Text #11

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5754. Min Act: -0.1700

Data Index: 4622937 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5533. Min Act: -0.1700

Data Index: 1961934 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5516. Min Act: -0.1700

Data Index: 7870076 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5723. Min Act: -0.1700

Data Index: 1779129 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5632. Min Act: -0.1700

Data Index: 1770239 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5515. Min Act: -0.1700

Data Index: 6851640 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5682. Min Act: -0.1700

Data Index: 5849848 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5826. Min Act: -0.1700

Data Index: 5804915 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 4.7722. Min Range: -4.7722

Max Act: 4.5584. Min Act: -0.1700

Data Index: 5711793 (Open Web Text)

Max Activating Token Index: 600