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

Dataset: Open Web Text

Neuron 2019 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: 3.7748. Min Range: -3.7748

Max Act: 3.7748. Min Act: -0.1700

Data Index: 1774023 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.7677. Min Act: -0.1700

Data Index: 4627285 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.7322. Min Act: -0.1700

Data Index: 5987123 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6352. Min Act: -0.1700

Data Index: 1906464 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6234. Min Act: -0.1700

Data Index: 527348 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6470. Min Act: -0.1700

Data Index: 1141982 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6326. Min Act: -0.1700

Data Index: 4878373 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6185. Min Act: -0.1700

Data Index: 6179147 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6289. Min Act: -0.1700

Data Index: 8130031 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6258. Min Act: -0.1700

Data Index: 2606769 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6108. Min Act: -0.1700

Data Index: 8437304 (Open Web Text)

Max Activating Token Index: 348

Text #11

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.5930. Min Act: -0.1700

Data Index: 2672958 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6198. Min Act: -0.1700

Data Index: 4836851 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6405. Min Act: -0.1700

Data Index: 227669 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6088. Min Act: -0.1700

Data Index: 7798454 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.5844. Min Act: -0.1700

Data Index: 2266107 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.5768. Min Act: -0.1700

Data Index: 490880 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.5838. Min Act: -0.1700

Data Index: 8180420 (Open Web Text)

Max Activating Token Index: 553

Text #18

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.5825. Min Act: -0.1700

Data Index: 6165677 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 3.7748. Min Range: -3.7748

Max Act: 3.6059. Min Act: -0.1700

Data Index: 6964812 (Open Web Text)

Max Activating Token Index: 502