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

Dataset: Open Web Text

Neuron 2197 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: 3.7512. Min Range: -3.7512

Max Act: 3.7512. Min Act: -0.1700

Data Index: 3135737 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6556. Min Act: -0.1700

Data Index: 5532831 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6709. Min Act: -0.1700

Data Index: 1607233 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6453. Min Act: -0.1700

Data Index: 322752 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6353. Min Act: -0.1700

Data Index: 8189890 (Open Web Text)

Max Activating Token Index: 777

Text #5

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6326. Min Act: -0.1700

Data Index: 3635608 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.6091. Min Act: -0.1700

Data Index: 2897460 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5903. Min Act: -0.1700

Data Index: 5718276 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5535. Min Act: -0.1700

Data Index: 1546969 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1302243 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5874. Min Act: -0.1700

Data Index: 4197078 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5613. Min Act: -0.1700

Data Index: 2086894 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5403. Min Act: -0.1700

Data Index: 6080533 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5552. Min Act: -0.1700

Data Index: 1767931 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5684. Min Act: -0.1700

Data Index: 3187558 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5482. Min Act: -0.1700

Data Index: 6683761 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5279. Min Act: -0.1700

Data Index: 702780 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5507. Min Act: -0.1700

Data Index: 4310384 (Open Web Text)

Max Activating Token Index: 903

Text #18

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5609. Min Act: -0.1700

Data Index: 8625613 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 3.7512. Min Range: -3.7512

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1208713 (Open Web Text)

Max Activating Token Index: 94