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

Dataset: Open Web Text

Neuron 534 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: 3.1021. Min Range: -3.1021

Max Act: 3.1021. Min Act: -0.1700

Data Index: 5252184 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9042. Min Act: -0.1700

Data Index: 559775 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.9038. Min Act: -0.1700

Data Index: 6793120 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8847. Min Act: -0.1700

Data Index: 4351344 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8829. Min Act: -0.1700

Data Index: 720959 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8812. Min Act: -0.1700

Data Index: 5020312 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8621. Min Act: -0.1700

Data Index: 628672 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8692. Min Act: -0.1700

Data Index: 5149907 (Open Web Text)

Max Activating Token Index: 585

Text #8

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8430. Min Act: -0.1700

Data Index: 8327583 (Open Web Text)

Max Activating Token Index: 747

Text #9

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8446. Min Act: -0.1700

Data Index: 2926348 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8525. Min Act: -0.1700

Data Index: 4996287 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8005. Min Act: -0.1700

Data Index: 884130 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8068. Min Act: -0.1700

Data Index: 6645084 (Open Web Text)

Max Activating Token Index: 669

Text #13

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8187. Min Act: -0.1700

Data Index: 3624475 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8025. Min Act: -0.1700

Data Index: 5363360 (Open Web Text)

Max Activating Token Index: 1006

Text #15

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8325. Min Act: -0.1700

Data Index: 6789048 (Open Web Text)

Max Activating Token Index: 571

Text #16

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.7764. Min Act: -0.1700

Data Index: 6230606 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8098. Min Act: -0.1700

Data Index: 2445130 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8060. Min Act: -0.1700

Data Index: 3950625 (Open Web Text)

Max Activating Token Index: 835

Text #19

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.8190. Min Act: -0.1697

Data Index: 1251599 (Open Web Text)

Max Activating Token Index: 949