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

Dataset: Open Web Text

Neuron 2290 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: 4.1623. Min Range: -4.1623

Max Act: 4.1623. Min Act: -0.1700

Data Index: 463349 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.1457. Min Act: -0.1700

Data Index: 5268874 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0896. Min Act: -0.1700

Data Index: 7621094 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0913. Min Act: -0.1700

Data Index: 3688297 (Open Web Text)

Max Activating Token Index: 865

Text #4

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0150. Min Act: -0.1700

Data Index: 6822296 (Open Web Text)

Max Activating Token Index: 711

Text #5

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0375. Min Act: -0.1700

Data Index: 5537931 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0096. Min Act: -0.1700

Data Index: 6818799 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 4.1623. Min Range: -4.1623

Max Act: 4.0100. Min Act: -0.1700

Data Index: 5592738 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9674. Min Act: -0.1700

Data Index: 6911998 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9613. Min Act: -0.1700

Data Index: 4877669 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9335. Min Act: -0.1700

Data Index: 75777 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9576. Min Act: -0.1700

Data Index: 1381635 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9453. Min Act: -0.1700

Data Index: 1279925 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9689. Min Act: -0.1700

Data Index: 2913594 (Open Web Text)

Max Activating Token Index: 182

Text #14

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9492. Min Act: -0.1700

Data Index: 4394293 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9277. Min Act: -0.1700

Data Index: 6877388 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9369. Min Act: -0.1700

Data Index: 5398461 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9028. Min Act: -0.1700

Data Index: 808578 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9444. Min Act: -0.1700

Data Index: 3927181 (Open Web Text)

Max Activating Token Index: 431

Text #19

Max Range: 4.1623. Min Range: -4.1623

Max Act: 3.9086. Min Act: -0.1700

Data Index: 4033998 (Open Web Text)

Max Activating Token Index: 903