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

Dataset: Open Web Text

Neuron 576 in Layer 3

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: 3.5874. Min Range: -3.5874

Max Act: 3.5874. Min Act: -0.1700

Data Index: 3720481 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4476. Min Act: -0.1700

Data Index: 2372580 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4350. Min Act: -0.1700

Data Index: 7174587 (Open Web Text)

Max Activating Token Index: 856

Text #3

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4392. Min Act: -0.1700

Data Index: 3297261 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4405. Min Act: -0.1700

Data Index: 5623668 (Open Web Text)

Max Activating Token Index: 749

Text #5

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4712. Min Act: -0.1700

Data Index: 5662642 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4422. Min Act: -0.1700

Data Index: 2277941 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4020. Min Act: -0.1700

Data Index: 8704718 (Open Web Text)

Max Activating Token Index: 598

Text #8

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4127. Min Act: -0.1700

Data Index: 5387926 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3894. Min Act: -0.1700

Data Index: 8717358 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4021. Min Act: -0.1700

Data Index: 275672 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.4152. Min Act: -0.1700

Data Index: 50896 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3750. Min Act: -0.1700

Data Index: 7035210 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3774. Min Act: -0.1700

Data Index: 6123103 (Open Web Text)

Max Activating Token Index: 962

Text #14

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3576. Min Act: -0.1700

Data Index: 7167223 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3602. Min Act: -0.1700

Data Index: 3345797 (Open Web Text)

Max Activating Token Index: 386

Text #16

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3696. Min Act: -0.1700

Data Index: 5397895 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3758. Min Act: -0.1700

Data Index: 3062453 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3340. Min Act: -0.1700

Data Index: 25159 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 3.5874. Min Range: -3.5874

Max Act: 3.3357. Min Act: -0.1700

Data Index: 425226 (Open Web Text)

Max Activating Token Index: 301