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

Dataset: Open Web Text

Neuron 296 in Layer 4

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: 3.4828. Min Range: -3.4828

Max Act: 3.4828. Min Act: -0.1700

Data Index: 5853773 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.3098. Min Act: -0.1700

Data Index: 6926153 (Open Web Text)

Max Activating Token Index: 993

Text #2

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.2771. Min Act: -0.1700

Data Index: 3714940 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.2307. Min Act: -0.1700

Data Index: 4396418 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.1658. Min Act: -0.1700

Data Index: 7371490 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1637376 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.2222. Min Act: -0.1700

Data Index: 4570514 (Open Web Text)

Max Activating Token Index: 721

Text #7

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.1845. Min Act: -0.1700

Data Index: 8103003 (Open Web Text)

Max Activating Token Index: 708

Text #8

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.1777. Min Act: -0.1700

Data Index: 1083080 (Open Web Text)

Max Activating Token Index: 562

Text #9

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.1373. Min Act: -0.1700

Data Index: 5239611 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.1025. Min Act: -0.1700

Data Index: 2430863 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0885. Min Act: -0.1700

Data Index: 6577753 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0376. Min Act: -0.1700

Data Index: 5668124 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0337. Min Act: -0.1700

Data Index: 5654917 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 3.4828. Min Range: -3.4828

Max Act: 2.9971. Min Act: -0.1700

Data Index: 5561798 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0200. Min Act: -0.1700

Data Index: 1881917 (Open Web Text)

Max Activating Token Index: 745

Text #16

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0251. Min Act: -0.1700

Data Index: 6374462 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0300. Min Act: -0.1700

Data Index: 362262 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0198. Min Act: -0.1700

Data Index: 66039 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 3.4828. Min Range: -3.4828

Max Act: 3.0225. Min Act: -0.1700

Data Index: 2659578 (Open Web Text)

Max Activating Token Index: 942