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

Dataset: Open Web Text

Neuron 2050 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: 6.0583. Min Range: -6.0583

Max Act: 6.0583. Min Act: -0.1700

Data Index: 1134557 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.9400. Min Act: -0.1700

Data Index: 8418353 (Open Web Text)

Max Activating Token Index: 626

Text #2

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.9136. Min Act: -0.1700

Data Index: 8722276 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.8944. Min Act: -0.1700

Data Index: 7252784 (Open Web Text)

Max Activating Token Index: 596

Text #4

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.8321. Min Act: -0.1700

Data Index: 5695822 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.8234. Min Act: -0.1700

Data Index: 3218397 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.8422. Min Act: -0.1700

Data Index: 3974282 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.8093. Min Act: -0.1700

Data Index: 3391349 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7904. Min Act: -0.1700

Data Index: 2506825 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7402. Min Act: -0.1700

Data Index: 1910964 (Open Web Text)

Max Activating Token Index: 119

Text #10

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7690. Min Act: -0.1700

Data Index: 8662227 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7724. Min Act: -0.1700

Data Index: 4935577 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7256. Min Act: -0.1700

Data Index: 5660663 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.7309. Min Act: -0.1700

Data Index: 6545253 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.6923. Min Act: -0.1700

Data Index: 7582366 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.6464. Min Act: -0.1700

Data Index: 3183120 (Open Web Text)

Max Activating Token Index: 237

Text #16

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.6226. Min Act: -0.1700

Data Index: 5149546 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.5797. Min Act: -0.1700

Data Index: 751752 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.5364. Min Act: -0.1700

Data Index: 1753639 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 6.0583. Min Range: -6.0583

Max Act: 5.5325. Min Act: -0.1700

Data Index: 5918154 (Open Web Text)

Max Activating Token Index: 120