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

Dataset: Open Web Text

Neuron 90 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: 3.3701. Min Range: -3.3701

Max Act: 3.3701. Min Act: -0.1700

Data Index: 3505352 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.2738. Min Act: -0.1700

Data Index: 4606497 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.2559. Min Act: -0.1700

Data Index: 4565801 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.2439. Min Act: -0.1700

Data Index: 2708246 (Open Web Text)

Max Activating Token Index: 784

Text #4

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.2162. Min Act: -0.1700

Data Index: 7641533 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.2037. Min Act: -0.1700

Data Index: 7977846 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1894. Min Act: -0.1700

Data Index: 994886 (Open Web Text)

Max Activating Token Index: 834

Text #7

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1679. Min Act: -0.1700

Data Index: 3680184 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1867. Min Act: -0.1700

Data Index: 3028428 (Open Web Text)

Max Activating Token Index: 916

Text #9

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1616. Min Act: -0.1700

Data Index: 1870867 (Open Web Text)

Max Activating Token Index: 832

Text #10

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1737. Min Act: -0.1700

Data Index: 3189581 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1361. Min Act: -0.1700

Data Index: 6802505 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1210. Min Act: -0.1700

Data Index: 5665276 (Open Web Text)

Max Activating Token Index: 931

Text #13

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1368. Min Act: -0.1700

Data Index: 2857367 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1192. Min Act: -0.1700

Data Index: 5902795 (Open Web Text)

Max Activating Token Index: 631

Text #15

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1356. Min Act: -0.1700

Data Index: 8378568 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1058. Min Act: -0.1700

Data Index: 4814315 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1034. Min Act: -0.1700

Data Index: 6113905 (Open Web Text)

Max Activating Token Index: 642

Text #18

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.0993. Min Act: -0.1700

Data Index: 8524497 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.1086. Min Act: -0.1700

Data Index: 4044162 (Open Web Text)

Max Activating Token Index: 624