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

Dataset: Open Web Text

Neuron 542 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: 3.5346. Min Range: -3.5346

Max Act: 3.5346. Min Act: -0.1700

Data Index: 7008796 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4468. Min Act: -0.1700

Data Index: 4865330 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4646. Min Act: -0.1700

Data Index: 8064451 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4479. Min Act: -0.1700

Data Index: 7008813 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3902. Min Act: -0.1700

Data Index: 7806717 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4017. Min Act: -0.1700

Data Index: 3087919 (Open Web Text)

Max Activating Token Index: 809

Text #6

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4134. Min Act: -0.1700

Data Index: 4048657 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4106. Min Act: -0.1700

Data Index: 7008810 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.4102. Min Act: -0.1700

Data Index: 7008829 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3590. Min Act: -0.1700

Data Index: 3087939 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3412. Min Act: -0.1700

Data Index: 6868460 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3322. Min Act: -0.1700

Data Index: 1372442 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3374. Min Act: -0.1700

Data Index: 251953 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3101. Min Act: -0.1700

Data Index: 1059076 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3068. Min Act: -0.1700

Data Index: 5175902 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.2784. Min Act: -0.1700

Data Index: 6594859 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3050. Min Act: -0.1700

Data Index: 7008817 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.2970. Min Act: -0.1700

Data Index: 5307474 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.3051. Min Act: -0.1700

Data Index: 3087935 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 3.5346. Min Range: -3.5346

Max Act: 3.2854. Min Act: -0.1700

Data Index: 3087933 (Open Web Text)

Max Activating Token Index: 26