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

Dataset: Open Web Text

Neuron 1738 in Layer 2

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: 4.7526. Min Range: -4.7526

Max Act: 4.7526. Min Act: -0.1700

Data Index: 6508812 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.6689. Min Act: -0.1700

Data Index: 5514744 (Open Web Text)

Max Activating Token Index: 64

Text #2

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.6457. Min Act: -0.1700

Data Index: 3731232 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5918. Min Act: -0.1700

Data Index: 2888979 (Open Web Text)

Max Activating Token Index: 577

Text #4

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.6270. Min Act: -0.1700

Data Index: 208100 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5951. Min Act: -0.1700

Data Index: 83138 (Open Web Text)

Max Activating Token Index: 964

Text #6

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5875. Min Act: -0.1700

Data Index: 5517567 (Open Web Text)

Max Activating Token Index: 138

Text #7

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5913. Min Act: -0.1700

Data Index: 4206849 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.6038. Min Act: -0.1700

Data Index: 3694550 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5703. Min Act: -0.1700

Data Index: 173329 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5784. Min Act: -0.1700

Data Index: 7968496 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5857. Min Act: -0.1700

Data Index: 7764477 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5731. Min Act: -0.1700

Data Index: 1339493 (Open Web Text)

Max Activating Token Index: 199

Text #13

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5889. Min Act: -0.1700

Data Index: 5893763 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5462. Min Act: -0.1700

Data Index: 4676589 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5539. Min Act: -0.1700

Data Index: 4763821 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5725. Min Act: -0.1700

Data Index: 5071104 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5571. Min Act: -0.1700

Data Index: 1815796 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5399. Min Act: -0.1700

Data Index: 3470647 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 4.7526. Min Range: -4.7526

Max Act: 4.5779. Min Act: -0.1700

Data Index: 2784079 (Open Web Text)

Max Activating Token Index: 723