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

Dataset: Open Web Text

Neuron 1822 in Layer 3

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: 4.1637. Min Range: -4.1637

Max Act: 4.1637. Min Act: -0.1700

Data Index: 71415 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9768. Min Act: -0.1700

Data Index: 7221500 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9657. Min Act: -0.1700

Data Index: 3607246 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9278. Min Act: -0.1700

Data Index: 5121873 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.9590. Min Act: -0.1700

Data Index: 4790406 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8990. Min Act: -0.1700

Data Index: 4771479 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8981. Min Act: -0.1700

Data Index: 2052773 (Open Web Text)

Max Activating Token Index: 654

Text #7

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8894. Min Act: -0.1700

Data Index: 6539330 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8412. Min Act: -0.1700

Data Index: 1117251 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8418. Min Act: -0.1700

Data Index: 6477699 (Open Web Text)

Max Activating Token Index: 168

Text #10

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8657. Min Act: -0.1700

Data Index: 1881080 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8406. Min Act: -0.1700

Data Index: 3977652 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8462. Min Act: -0.1700

Data Index: 8026087 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8485. Min Act: -0.1700

Data Index: 1443560 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8552. Min Act: -0.1700

Data Index: 3759705 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8173. Min Act: -0.1700

Data Index: 5510961 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8125. Min Act: -0.1700

Data Index: 6740001 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8239. Min Act: -0.1700

Data Index: 6532743 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8237. Min Act: -0.1700

Data Index: 6350008 (Open Web Text)

Max Activating Token Index: 477

Text #19

Max Range: 4.1637. Min Range: -4.1637

Max Act: 3.8140. Min Act: -0.1700

Data Index: 6204941 (Open Web Text)

Max Activating Token Index: 310