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

Dataset: Open Web Text

Neuron 2418 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: 4.3776. Min Range: -4.3776

Max Act: 4.3776. Min Act: -0.1700

Data Index: 2505292 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.3420. Min Act: -0.1700

Data Index: 6298460 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.3640. Min Act: -0.1700

Data Index: 699644 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.3186. Min Act: -0.1700

Data Index: 8388391 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.3145. Min Act: -0.1700

Data Index: 1116178 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.3348. Min Act: -0.1700

Data Index: 5179966 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2999. Min Act: -0.1700

Data Index: 7284167 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2968. Min Act: -0.1700

Data Index: 1473798 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2818. Min Act: -0.1700

Data Index: 934024 (Open Web Text)

Max Activating Token Index: 997

Text #9

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2901. Min Act: -0.1700

Data Index: 132799 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2737. Min Act: -0.1700

Data Index: 6260270 (Open Web Text)

Max Activating Token Index: 384

Text #11

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2491. Min Act: -0.1700

Data Index: 5814154 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2201. Min Act: -0.1700

Data Index: 4039602 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2239. Min Act: -0.1700

Data Index: 6136051 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2267. Min Act: -0.1700

Data Index: 5284465 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2262. Min Act: -0.1700

Data Index: 2127309 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2392. Min Act: -0.1700

Data Index: 3107661 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2265. Min Act: -0.1700

Data Index: 5807694 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2415. Min Act: -0.1700

Data Index: 7318653 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.3776. Min Range: -4.3776

Max Act: 4.2368. Min Act: -0.1700

Data Index: 5548149 (Open Web Text)

Max Activating Token Index: 213