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

Dataset: Open Web Text

Neuron 1899 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: 3.8050. Min Range: -3.8050

Max Act: 3.8050. Min Act: -0.1700

Data Index: 8150628 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.7254. Min Act: -0.1700

Data Index: 1797414 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.7138. Min Act: -0.1700

Data Index: 6180070 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6986. Min Act: -0.1700

Data Index: 1871081 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6820. Min Act: -0.1700

Data Index: 6824607 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6793. Min Act: -0.1700

Data Index: 6342517 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6638. Min Act: -0.1700

Data Index: 3651179 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6821. Min Act: -0.1700

Data Index: 7323724 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6442. Min Act: -0.1700

Data Index: 5475771 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6424. Min Act: -0.1700

Data Index: 6937714 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6247. Min Act: -0.1700

Data Index: 5511738 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6308. Min Act: -0.1700

Data Index: 7582548 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6388. Min Act: -0.1700

Data Index: 8548398 (Open Web Text)

Max Activating Token Index: 585

Text #13

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6352. Min Act: -0.1700

Data Index: 3903326 (Open Web Text)

Max Activating Token Index: 152

Text #14

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.6010. Min Act: -0.1700

Data Index: 7615461 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.5968. Min Act: -0.1700

Data Index: 8315663 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.5970. Min Act: -0.1700

Data Index: 4296880 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.5862. Min Act: -0.1700

Data Index: 4949323 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.5896. Min Act: -0.1700

Data Index: 644609 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 3.8050. Min Range: -3.8050

Max Act: 3.5861. Min Act: -0.1700

Data Index: 3770855 (Open Web Text)

Max Activating Token Index: 217