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

Dataset: Open Web Text

Neuron 721 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: 3.3494. Min Range: -3.3494

Max Act: 3.3494. Min Act: -0.1700

Data Index: 5581115 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1961. Min Act: -0.1700

Data Index: 2539208 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.2113. Min Act: -0.1700

Data Index: 8475031 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.2025. Min Act: -0.1700

Data Index: 1079418 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.2239. Min Act: -0.1700

Data Index: 4366351 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1851. Min Act: -0.1700

Data Index: 3982074 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0924. Min Act: -0.1700

Data Index: 8615234 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1436. Min Act: -0.1700

Data Index: 6248350 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1214. Min Act: -0.1700

Data Index: 3697208 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1350. Min Act: -0.1700

Data Index: 8436935 (Open Web Text)

Max Activating Token Index: 295

Text #10

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1376. Min Act: -0.1700

Data Index: 1850890 (Open Web Text)

Max Activating Token Index: 746

Text #11

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0891. Min Act: -0.1700

Data Index: 4725759 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1019. Min Act: -0.1700

Data Index: 8256433 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0909. Min Act: -0.1700

Data Index: 2519714 (Open Web Text)

Max Activating Token Index: 152

Text #14

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1066. Min Act: -0.1700

Data Index: 118671 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0591. Min Act: -0.1700

Data Index: 4597232 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0501. Min Act: -0.1700

Data Index: 6739582 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0396. Min Act: -0.1700

Data Index: 4972259 (Open Web Text)

Max Activating Token Index: 549

Text #18

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0849. Min Act: -0.1700

Data Index: 3982075 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0668. Min Act: -0.1700

Data Index: 8586930 (Open Web Text)

Max Activating Token Index: 869