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

Dataset: Open Web Text

Neuron 2732 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: 4.9571. Min Range: -4.9571

Max Act: 4.9571. Min Act: -0.1700

Data Index: 2350184 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.8201. Min Act: -0.1700

Data Index: 1803517 (Open Web Text)

Max Activating Token Index: 373

Text #2

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.8513. Min Act: -0.1700

Data Index: 2122842 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.8460. Min Act: -0.1700

Data Index: 2111368 (Open Web Text)

Max Activating Token Index: 180

Text #4

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.7232. Min Act: -0.1700

Data Index: 7384393 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6809. Min Act: -0.1700

Data Index: 8463897 (Open Web Text)

Max Activating Token Index: 677

Text #6

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6779. Min Act: -0.1700

Data Index: 2704774 (Open Web Text)

Max Activating Token Index: 275

Text #7

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6832. Min Act: -0.1700

Data Index: 3900103 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6515. Min Act: -0.1700

Data Index: 85935 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6885. Min Act: -0.1700

Data Index: 6177404 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6257. Min Act: -0.1700

Data Index: 4615605 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6733. Min Act: -0.1700

Data Index: 2098447 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6244. Min Act: -0.1700

Data Index: 4307419 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6143. Min Act: -0.1700

Data Index: 4983778 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.5929. Min Act: -0.1700

Data Index: 2896868 (Open Web Text)

Max Activating Token Index: 158

Text #15

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6136. Min Act: -0.1700

Data Index: 5049859 (Open Web Text)

Max Activating Token Index: 318

Text #16

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.5986. Min Act: -0.1700

Data Index: 5515033 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6039. Min Act: -0.1700

Data Index: 2503288 (Open Web Text)

Max Activating Token Index: 553

Text #18

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6147. Min Act: -0.1700

Data Index: 5667083 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 4.9571. Min Range: -4.9571

Max Act: 4.6074. Min Act: -0.1700

Data Index: 1391911 (Open Web Text)

Max Activating Token Index: 417