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

Dataset: Open Web Text

Neuron 1930 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: 5.7710. Min Range: -5.7710

Max Act: 5.7710. Min Act: -0.1700

Data Index: 7934362 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.7596. Min Act: -0.1700

Data Index: 6863972 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.7280. Min Act: -0.1700

Data Index: 209318 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.7083. Min Act: -0.1700

Data Index: 3451327 (Open Web Text)

Max Activating Token Index: 417

Text #4

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6818. Min Act: -0.1700

Data Index: 3994648 (Open Web Text)

Max Activating Token Index: 368

Text #5

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6288. Min Act: -0.1700

Data Index: 3299676 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6722. Min Act: -0.1700

Data Index: 1915092 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6510. Min Act: -0.1700

Data Index: 2257658 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6926. Min Act: -0.1700

Data Index: 1666895 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6704. Min Act: -0.1700

Data Index: 5048410 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6636. Min Act: -0.1700

Data Index: 8117080 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6600. Min Act: -0.1700

Data Index: 6000865 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6358. Min Act: -0.1700

Data Index: 2090495 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6330. Min Act: -0.1700

Data Index: 5657988 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6208. Min Act: -0.1700

Data Index: 2210096 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6391. Min Act: -0.1700

Data Index: 1705965 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6032. Min Act: -0.1700

Data Index: 2076783 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6061. Min Act: -0.1700

Data Index: 6542247 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6204. Min Act: -0.1700

Data Index: 6246822 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 5.7710. Min Range: -5.7710

Max Act: 5.6014. Min Act: -0.1700

Data Index: 2370335 (Open Web Text)

Max Activating Token Index: 437