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

Dataset: Open Web Text

Neuron 2273 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: 3.2944. Min Range: -3.2944

Max Act: 3.2944. Min Act: -0.1700

Data Index: 6838067 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.1421. Min Act: -0.1700

Data Index: 5466254 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.1519. Min Act: -0.1700

Data Index: 6224611 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.0700. Min Act: -0.1700

Data Index: 8496436 (Open Web Text)

Max Activating Token Index: 324

Text #4

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.0369. Min Act: -0.1700

Data Index: 3055267 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.0261. Min Act: -0.1700

Data Index: 7852939 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.0233. Min Act: -0.1700

Data Index: 2204144 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9914. Min Act: -0.1700

Data Index: 201814 (Open Web Text)

Max Activating Token Index: 782

Text #8

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.0056. Min Act: -0.1700

Data Index: 8423337 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9864. Min Act: -0.1700

Data Index: 7318668 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9889. Min Act: -0.1700

Data Index: 2434955 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9820. Min Act: -0.1700

Data Index: 1274183 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9738. Min Act: -0.1700

Data Index: 4245650 (Open Web Text)

Max Activating Token Index: 893

Text #13

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9771. Min Act: -0.1700

Data Index: 6270134 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9806. Min Act: -0.1700

Data Index: 2042326 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9547. Min Act: -0.1700

Data Index: 748502 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9662. Min Act: -0.1700

Data Index: 3963300 (Open Web Text)

Max Activating Token Index: 647

Text #17

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9933. Min Act: -0.1700

Data Index: 3648369 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9647. Min Act: -0.1700

Data Index: 7121147 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9682. Min Act: -0.1700

Data Index: 5506562 (Open Web Text)

Max Activating Token Index: 380