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

Dataset: Open Web Text

Neuron 2475 in Layer 3

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: 3.7729. Min Range: -3.7729

Max Act: 3.7729. Min Act: -0.1700

Data Index: 2345996 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.7473. Min Act: -0.1700

Data Index: 6921370 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.7012. Min Act: -0.1700

Data Index: 3644328 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6893. Min Act: -0.1700

Data Index: 65287 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6981. Min Act: -0.1700

Data Index: 3570358 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6874. Min Act: -0.1700

Data Index: 5378151 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6150. Min Act: -0.1700

Data Index: 7370622 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6275. Min Act: -0.1700

Data Index: 7852910 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1833923 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6276. Min Act: -0.1700

Data Index: 307110 (Open Web Text)

Max Activating Token Index: 934

Text #10

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6193. Min Act: -0.1700

Data Index: 3583920 (Open Web Text)

Max Activating Token Index: 607

Text #11

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6281. Min Act: -0.1700

Data Index: 1966519 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6144. Min Act: -0.1700

Data Index: 3994544 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1617472 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5612. Min Act: -0.1700

Data Index: 7747359 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5899. Min Act: -0.1700

Data Index: 2101834 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.6163. Min Act: -0.1700

Data Index: 4212815 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5529. Min Act: -0.1700

Data Index: 285502 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5759. Min Act: -0.1700

Data Index: 6217486 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 3.7729. Min Range: -3.7729

Max Act: 3.5772. Min Act: -0.1700

Data Index: 5604636 (Open Web Text)

Max Activating Token Index: 197