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

Dataset: Open Web Text

Neuron 2547 in Layer 6

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: 4.9897. Min Range: -4.9897

Max Act: 4.9647. Min Act: -0.1700

Data Index: 675541 (Open Web Text)

Max Activating Token Index: 687

Text #1

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.9897. Min Act: -0.1700

Data Index: 1950947 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.9564. Min Act: -0.1700

Data Index: 7856929 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.9211. Min Act: -0.1700

Data Index: 721827 (Open Web Text)

Max Activating Token Index: 351

Text #4

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8789. Min Act: -0.1700

Data Index: 2051578 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8838. Min Act: -0.1700

Data Index: 5058978 (Open Web Text)

Max Activating Token Index: 393

Text #6

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8696. Min Act: -0.1700

Data Index: 3200192 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8137. Min Act: -0.1700

Data Index: 3437222 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8592. Min Act: -0.1700

Data Index: 7691711 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7914. Min Act: -0.1700

Data Index: 871706 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7916. Min Act: -0.1700

Data Index: 8219428 (Open Web Text)

Max Activating Token Index: 859

Text #11

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8291. Min Act: -0.1700

Data Index: 2611111 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7905. Min Act: -0.1700

Data Index: 6910616 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.8205. Min Act: -0.1700

Data Index: 3393233 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7761. Min Act: -0.1700

Data Index: 8542115 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7849. Min Act: -0.1700

Data Index: 5923917 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7586. Min Act: -0.1700

Data Index: 7624814 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7588. Min Act: -0.1700

Data Index: 3153815 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7492. Min Act: -0.1700

Data Index: 2977608 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 4.9897. Min Range: -4.9897

Max Act: 4.7386. Min Act: -0.1700

Data Index: 7631150 (Open Web Text)

Max Activating Token Index: 480