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

Dataset: Open Web Text

Neuron 384 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: 3.7514. Min Range: -3.7514

Max Act: 3.7468. Min Act: -0.1700

Data Index: 5489298 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1657089 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.6161. Min Act: -0.1700

Data Index: 5808594 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5731. Min Act: -0.1700

Data Index: 4355330 (Open Web Text)

Max Activating Token Index: 249

Text #4

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5720. Min Act: -0.1700

Data Index: 1740960 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5724. Min Act: -0.1700

Data Index: 7694293 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5810. Min Act: -0.1700

Data Index: 4578178 (Open Web Text)

Max Activating Token Index: 330

Text #7

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5640. Min Act: -0.1700

Data Index: 2342945 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5455. Min Act: -0.1700

Data Index: 8277203 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5784. Min Act: -0.1700

Data Index: 6277646 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5535. Min Act: -0.1700

Data Index: 5214023 (Open Web Text)

Max Activating Token Index: 921

Text #11

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5451. Min Act: -0.1700

Data Index: 4559966 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5314. Min Act: -0.1700

Data Index: 8828872 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5273. Min Act: -0.1700

Data Index: 3726256 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5160. Min Act: -0.1700

Data Index: 1178198 (Open Web Text)

Max Activating Token Index: 764

Text #15

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5360. Min Act: -0.1700

Data Index: 3725373 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5192. Min Act: -0.1700

Data Index: 6725270 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5229. Min Act: -0.1700

Data Index: 1951410 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4812. Min Act: -0.1700

Data Index: 8520270 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5211. Min Act: -0.1700

Data Index: 4408837 (Open Web Text)

Max Activating Token Index: 832