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

Dataset: Open Web Text

Neuron 981 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: 3.7324. Min Range: -3.7324

Max Act: 3.7324. Min Act: -0.1700

Data Index: 2144559 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7168. Min Act: -0.1700

Data Index: 4619212 (Open Web Text)

Max Activating Token Index: 550

Text #2

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6639. Min Act: -0.1700

Data Index: 5811232 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6667. Min Act: -0.1700

Data Index: 5750618 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1625429 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6630. Min Act: -0.1700

Data Index: 8728727 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6606. Min Act: -0.1700

Data Index: 1807178 (Open Web Text)

Max Activating Token Index: 452

Text #7

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6652. Min Act: -0.1700

Data Index: 8407725 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6273. Min Act: -0.1700

Data Index: 3001372 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6464. Min Act: -0.1700

Data Index: 8455491 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6194. Min Act: -0.1700

Data Index: 8565204 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6046. Min Act: -0.1700

Data Index: 8180768 (Open Web Text)

Max Activating Token Index: 941

Text #12

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6067. Min Act: -0.1700

Data Index: 3934131 (Open Web Text)

Max Activating Token Index: 297

Text #13

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6060. Min Act: -0.1700

Data Index: 3491567 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5988. Min Act: -0.1700

Data Index: 8493232 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5666. Min Act: -0.1700

Data Index: 2250534 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5850. Min Act: -0.1700

Data Index: 618251 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6237. Min Act: -0.1700

Data Index: 7075326 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6006. Min Act: -0.1700

Data Index: 1738027 (Open Web Text)

Max Activating Token Index: 209

Text #19

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6029. Min Act: -0.1700

Data Index: 2572635 (Open Web Text)

Max Activating Token Index: 582