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

Dataset: Open Web Text

Neuron 1244 in Layer 1

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: 1.8394. Min Range: -1.8394

Max Act: 1.8394. Min Act: -0.1671

Data Index: 7768757 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8349. Min Act: -0.1700

Data Index: 48252 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8099. Min Act: -0.1698

Data Index: 3742212 (Open Web Text)

Max Activating Token Index: 179

Text #3

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7902. Min Act: -0.1575

Data Index: 8127305 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7694. Min Act: -0.1668

Data Index: 6643163 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7697. Min Act: -0.1695

Data Index: 934013 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7621. Min Act: -0.1693

Data Index: 1403972 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7587. Min Act: -0.1699

Data Index: 2416230 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7490. Min Act: -0.1698

Data Index: 8548223 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7401. Min Act: -0.1700

Data Index: 1875638 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7327. Min Act: -0.1669

Data Index: 8172551 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7272. Min Act: -0.1700

Data Index: 3593593 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7265. Min Act: -0.1699

Data Index: 8213924 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7073. Min Act: -0.1488

Data Index: 7886865 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7057. Min Act: -0.1700

Data Index: 7110017 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7103. Min Act: -0.1634

Data Index: 2419042 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7084. Min Act: -0.1699

Data Index: 5931490 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7102. Min Act: -0.1688

Data Index: 1140849 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.7041. Min Act: -0.1700

Data Index: 4357801 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.6964. Min Act: -0.1700

Data Index: 4510176 (Open Web Text)

Max Activating Token Index: 20