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

Dataset: Open Web Text

Neuron 778 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: 4.6768. Min Range: -4.6768

Max Act: 4.6768. Min Act: -0.1700

Data Index: 2643619 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6632. Min Act: -0.1700

Data Index: 5750446 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6722. Min Act: -0.1700

Data Index: 4862489 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6127. Min Act: -0.1700

Data Index: 6227882 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6291. Min Act: -0.1700

Data Index: 1530229 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6289. Min Act: -0.1700

Data Index: 2180711 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6126. Min Act: -0.1700

Data Index: 8675809 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6216. Min Act: -0.1700

Data Index: 5889188 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6045. Min Act: -0.1700

Data Index: 6264877 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.6117. Min Act: -0.1700

Data Index: 1407141 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5881. Min Act: -0.1700

Data Index: 4985864 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5795. Min Act: -0.1700

Data Index: 5321171 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5746. Min Act: -0.1700

Data Index: 3539676 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5597. Min Act: -0.1700

Data Index: 7668716 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5374. Min Act: -0.1700

Data Index: 4490353 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5344. Min Act: -0.1700

Data Index: 2749328 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5428. Min Act: -0.1700

Data Index: 2934548 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5431. Min Act: -0.1700

Data Index: 341447 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5500. Min Act: -0.1700

Data Index: 1889859 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 4.6768. Min Range: -4.6768

Max Act: 4.5448. Min Act: -0.1700

Data Index: 4463622 (Open Web Text)

Max Activating Token Index: 877