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

Dataset: Open Web Text

Neuron 1356 in Layer 5

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: 3.8752. Min Range: -3.8752

Max Act: 3.8752. Min Act: -0.1700

Data Index: 5076589 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8403. Min Act: -0.1700

Data Index: 1404205 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8110. Min Act: -0.1700

Data Index: 7101252 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8189. Min Act: -0.1700

Data Index: 7481515 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.8281. Min Act: -0.1700

Data Index: 6779986 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7819. Min Act: -0.1700

Data Index: 8502654 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7675. Min Act: -0.1700

Data Index: 2600214 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7367. Min Act: -0.1700

Data Index: 4529859 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7235. Min Act: -0.1700

Data Index: 7847497 (Open Web Text)

Max Activating Token Index: 420

Text #9

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7117. Min Act: -0.1700

Data Index: 6037872 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7112. Min Act: -0.1700

Data Index: 4476257 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6927. Min Act: -0.1700

Data Index: 8570559 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6999. Min Act: -0.1700

Data Index: 8275383 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.7059. Min Act: -0.1700

Data Index: 8754311 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6876. Min Act: -0.1700

Data Index: 8369756 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6608. Min Act: -0.1700

Data Index: 3949291 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6559. Min Act: -0.1700

Data Index: 64577 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6699. Min Act: -0.1700

Data Index: 8729329 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6447. Min Act: -0.1700

Data Index: 8172990 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.8752. Min Range: -3.8752

Max Act: 3.6568. Min Act: -0.1700

Data Index: 2299618 (Open Web Text)

Max Activating Token Index: 568