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

Dataset: Open Web Text

Neuron 2468 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: 4.1715. Min Range: -4.1715

Max Act: 4.1715. Min Act: -0.1700

Data Index: 1239661 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0526. Min Act: -0.1700

Data Index: 6983815 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0275. Min Act: -0.1700

Data Index: 3313764 (Open Web Text)

Max Activating Token Index: 179

Text #3

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0245. Min Act: -0.1700

Data Index: 7731371 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0361. Min Act: -0.1700

Data Index: 6273878 (Open Web Text)

Max Activating Token Index: 791

Text #5

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0389. Min Act: -0.1700

Data Index: 4415271 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0036. Min Act: -0.1700

Data Index: 4751084 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0262. Min Act: -0.1700

Data Index: 6225131 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0098. Min Act: -0.1700

Data Index: 470165 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9911. Min Act: -0.1700

Data Index: 2288496 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9902. Min Act: -0.1700

Data Index: 1927623 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 4.1715. Min Range: -4.1715

Max Act: 4.0006. Min Act: -0.1700

Data Index: 5901718 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9908. Min Act: -0.1700

Data Index: 1702555 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9824. Min Act: -0.1700

Data Index: 7380907 (Open Web Text)

Max Activating Token Index: 711

Text #14

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9371. Min Act: -0.1700

Data Index: 3184714 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9536. Min Act: -0.1700

Data Index: 7412653 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9529. Min Act: -0.1700

Data Index: 1806075 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9603. Min Act: -0.1700

Data Index: 4869877 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9368. Min Act: -0.1700

Data Index: 3673195 (Open Web Text)

Max Activating Token Index: 386

Text #19

Max Range: 4.1715. Min Range: -4.1715

Max Act: 3.9619. Min Act: -0.1700

Data Index: 7269 (Open Web Text)

Max Activating Token Index: 526