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

Dataset: Open Web Text

Neuron 961 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: 4.6152. Min Range: -4.6152

Max Act: 4.6152. Min Act: -0.1700

Data Index: 2986486 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.4648. Min Act: -0.1700

Data Index: 5629730 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.4502. Min Act: -0.1700

Data Index: 7373062 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.4084. Min Act: -0.1700

Data Index: 1319238 (Open Web Text)

Max Activating Token Index: 506

Text #4

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.4164. Min Act: -0.1700

Data Index: 5003659 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3679. Min Act: -0.1700

Data Index: 6214824 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3919. Min Act: -0.1700

Data Index: 7436216 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3540. Min Act: -0.1700

Data Index: 6918844 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3260. Min Act: -0.1700

Data Index: 3756583 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3220. Min Act: -0.1700

Data Index: 1038031 (Open Web Text)

Max Activating Token Index: 414

Text #10

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3200. Min Act: -0.1700

Data Index: 5955499 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2801. Min Act: -0.1700

Data Index: 7980129 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2799. Min Act: -0.1700

Data Index: 6103936 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2783. Min Act: -0.1700

Data Index: 6446687 (Open Web Text)

Max Activating Token Index: 846

Text #14

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2717. Min Act: -0.1700

Data Index: 6395982 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.3005. Min Act: -0.1700

Data Index: 4229599 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2769. Min Act: -0.1700

Data Index: 6169638 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2680. Min Act: -0.1700

Data Index: 7916539 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2464. Min Act: -0.1700

Data Index: 2179663 (Open Web Text)

Max Activating Token Index: 296

Text #19

Max Range: 4.6152. Min Range: -4.6152

Max Act: 4.2357. Min Act: -0.1700

Data Index: 304711 (Open Web Text)

Max Activating Token Index: 7