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

Dataset: Open Web Text

Neuron 2800 in Layer 5

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: 4.2851. Min Range: -4.2851

Max Act: 4.2851. Min Act: -0.1700

Data Index: 5195421 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0446. Min Act: -0.1700

Data Index: 6199603 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 4.2851. Min Range: -4.2851

Max Act: 4.0378. Min Act: -0.1700

Data Index: 291857 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9768. Min Act: -0.1700

Data Index: 4536131 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9910. Min Act: -0.1700

Data Index: 2233535 (Open Web Text)

Max Activating Token Index: 758

Text #5

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9687. Min Act: -0.1700

Data Index: 7560690 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9534. Min Act: -0.1700

Data Index: 3098315 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9089. Min Act: -0.1700

Data Index: 8662391 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8673. Min Act: -0.1700

Data Index: 3088463 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9281. Min Act: -0.1700

Data Index: 1747786 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.9008. Min Act: -0.1700

Data Index: 8262533 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8973. Min Act: -0.1700

Data Index: 3624725 (Open Web Text)

Max Activating Token Index: 248

Text #12

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8932. Min Act: -0.1700

Data Index: 1739643 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8606. Min Act: -0.1700

Data Index: 1921674 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8495. Min Act: -0.1700

Data Index: 4230220 (Open Web Text)

Max Activating Token Index: 767

Text #15

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8233. Min Act: -0.1700

Data Index: 3340076 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8237. Min Act: -0.1700

Data Index: 788610 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8267. Min Act: -0.1700

Data Index: 1208155 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.8238. Min Act: -0.1700

Data Index: 2993950 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 4.2851. Min Range: -4.2851

Max Act: 3.7742. Min Act: -0.1700

Data Index: 4576940 (Open Web Text)

Max Activating Token Index: 559