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

Dataset: Open Web Text

Neuron 119 in Layer 6

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: 3.3702. Min Range: -3.3702

Max Act: 3.3702. Min Act: -0.1700

Data Index: 4436457 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.1567. Min Act: -0.1700

Data Index: 6827749 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.1252. Min Act: -0.1700

Data Index: 642837 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.1075. Min Act: -0.1700

Data Index: 6590775 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.1011. Min Act: -0.1700

Data Index: 3167340 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0887. Min Act: -0.1700

Data Index: 4583212 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0588. Min Act: -0.1700

Data Index: 3290736 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0720. Min Act: -0.1700

Data Index: 5596628 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0541. Min Act: -0.1700

Data Index: 4904823 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0738. Min Act: -0.1700

Data Index: 2493870 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0537. Min Act: -0.1700

Data Index: 7358507 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0545. Min Act: -0.1700

Data Index: 668791 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0704. Min Act: -0.1700

Data Index: 1583577 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0670. Min Act: -0.1700

Data Index: 7553415 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0687. Min Act: -0.1700

Data Index: 7589057 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0618. Min Act: -0.1700

Data Index: 7289625 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0356. Min Act: -0.1700

Data Index: 5098071 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0462. Min Act: -0.1700

Data Index: 6396012 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0448. Min Act: -0.1700

Data Index: 1687954 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0281. Min Act: -0.1700

Data Index: 3351265 (Open Web Text)

Max Activating Token Index: 135