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

Dataset: Open Web Text

Neuron 2511 in Layer 2

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: 1.7627. Min Range: -1.7627

Max Act: 1.7627. Min Act: -0.1700

Data Index: 8129929 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7582. Min Act: -0.1700

Data Index: 8760686 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7230. Min Act: -0.1700

Data Index: 3943987 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7334. Min Act: -0.1700

Data Index: 8470731 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7257. Min Act: -0.1697

Data Index: 2934955 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7225. Min Act: -0.1700

Data Index: 7362352 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7176. Min Act: -0.1700

Data Index: 4970663 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.7105. Min Act: -0.1700

Data Index: 8401273 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6929. Min Act: -0.1700

Data Index: 3164147 (Open Web Text)

Max Activating Token Index: 690

Text #9

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6677. Min Act: -0.1700

Data Index: 3648947 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6673. Min Act: -0.1700

Data Index: 5517665 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6667. Min Act: -0.1700

Data Index: 6587720 (Open Web Text)

Max Activating Token Index: 235

Text #12

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6752. Min Act: -0.1700

Data Index: 4170299 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6688. Min Act: -0.1700

Data Index: 3514537 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6671. Min Act: -0.1700

Data Index: 8136375 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6579. Min Act: -0.1700

Data Index: 6626408 (Open Web Text)

Max Activating Token Index: 183

Text #16

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6590. Min Act: -0.1700

Data Index: 6867026 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6710. Min Act: -0.1700

Data Index: 1467793 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6523. Min Act: -0.1700

Data Index: 8144670 (Open Web Text)

Max Activating Token Index: 451

Text #19

Max Range: 1.7627. Min Range: -1.7627

Max Act: 1.6400. Min Act: -0.1700

Data Index: 2655678 (Open Web Text)

Max Activating Token Index: 743