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

Dataset: Open Web Text

Neuron 472 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: 4.7630. Min Range: -4.7630

Max Act: 4.7630. Min Act: -0.1700

Data Index: 4342881 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.7503. Min Act: -0.1700

Data Index: 6716625 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6936. Min Act: -0.1700

Data Index: 7380217 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.7024. Min Act: -0.1700

Data Index: 3814915 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6847. Min Act: -0.1700

Data Index: 6867945 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6922. Min Act: -0.1700

Data Index: 6729001 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6929. Min Act: -0.1700

Data Index: 6726448 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6773. Min Act: -0.1700

Data Index: 6937203 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6323. Min Act: -0.1700

Data Index: 1954295 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6259. Min Act: -0.1700

Data Index: 6084972 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6351. Min Act: -0.1700

Data Index: 3262272 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6193. Min Act: -0.1700

Data Index: 2054747 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6248. Min Act: -0.1700

Data Index: 1747513 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6015. Min Act: -0.1700

Data Index: 2491910 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6071. Min Act: -0.1700

Data Index: 6565341 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6033. Min Act: -0.1700

Data Index: 5122418 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.5943. Min Act: -0.1700

Data Index: 255395 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6031. Min Act: -0.1700

Data Index: 3546306 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.6074. Min Act: -0.1700

Data Index: 1468072 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.7630. Min Range: -4.7630

Max Act: 4.5961. Min Act: -0.1700

Data Index: 2049769 (Open Web Text)

Max Activating Token Index: 616