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

Dataset: Open Web Text

Neuron 6 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: 3.5633. Min Range: -3.5633

Max Act: 3.5633. Min Act: -0.1700

Data Index: 5610515 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5352. Min Act: -0.1700

Data Index: 7679718 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5145. Min Act: -0.1700

Data Index: 7793219 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5088. Min Act: -0.1700

Data Index: 6263809 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5361. Min Act: -0.1700

Data Index: 4329487 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4893. Min Act: -0.1700

Data Index: 3597243 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4744. Min Act: -0.1700

Data Index: 4319253 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5023. Min Act: -0.1700

Data Index: 7669480 (Open Web Text)

Max Activating Token Index: 720

Text #8

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.5274. Min Act: -0.1700

Data Index: 7496047 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4775. Min Act: -0.1700

Data Index: 3706760 (Open Web Text)

Max Activating Token Index: 890

Text #10

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4564. Min Act: -0.1700

Data Index: 6852500 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4533. Min Act: -0.1700

Data Index: 5650577 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4512. Min Act: -0.1700

Data Index: 7378627 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4387. Min Act: -0.1700

Data Index: 4285063 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4343. Min Act: -0.1700

Data Index: 144607 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4588. Min Act: -0.1700

Data Index: 4007318 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4518. Min Act: -0.1700

Data Index: 1134111 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4260. Min Act: -0.1700

Data Index: 4315173 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4268. Min Act: -0.1700

Data Index: 3878837 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.5633. Min Range: -3.5633

Max Act: 3.4225. Min Act: -0.1700

Data Index: 5618335 (Open Web Text)

Max Activating Token Index: 675