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

Dataset: Open Web Text

Neuron 3016 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: 4.0851. Min Range: -4.0851

Max Act: 4.0851. Min Act: -0.1700

Data Index: 5501967 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 4.0851. Min Range: -4.0851

Max Act: 4.0515. Min Act: -0.1700

Data Index: 2233594 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 4.0851. Min Range: -4.0851

Max Act: 4.0128. Min Act: -0.1700

Data Index: 2494022 (Open Web Text)

Max Activating Token Index: 658

Text #3

Max Range: 4.0851. Min Range: -4.0851

Max Act: 4.0036. Min Act: -0.1700

Data Index: 8384116 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.9286. Min Act: -0.1700

Data Index: 7164084 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.9333. Min Act: -0.1700

Data Index: 7598751 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.9061. Min Act: -0.1700

Data Index: 6524522 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.9230. Min Act: -0.1700

Data Index: 8384118 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8956. Min Act: -0.1700

Data Index: 4271969 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8792. Min Act: -0.1700

Data Index: 8803856 (Open Web Text)

Max Activating Token Index: 737

Text #10

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8800. Min Act: -0.1700

Data Index: 7164085 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8809. Min Act: -0.1700

Data Index: 3319079 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8264. Min Act: -0.1700

Data Index: 312142 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8521. Min Act: -0.1700

Data Index: 8384117 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8559. Min Act: -0.1700

Data Index: 2902747 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8416. Min Act: -0.1700

Data Index: 3784548 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8787. Min Act: -0.1700

Data Index: 2817416 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8544. Min Act: -0.1700

Data Index: 473579 (Open Web Text)

Max Activating Token Index: 497

Text #18

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8596. Min Act: -0.1700

Data Index: 6821624 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 4.0851. Min Range: -4.0851

Max Act: 3.8530. Min Act: -0.1700

Data Index: 1507834 (Open Web Text)

Max Activating Token Index: 649