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

Dataset: Open Web Text

Neuron 741 in Layer 1

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: 1.2444. Min Range: -1.2444

Max Act: 1.2444. Min Act: -0.1700

Data Index: 2532238 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2124. Min Act: -0.1700

Data Index: 4763914 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2167. Min Act: -0.1700

Data Index: 1593232 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2048. Min Act: -0.1698

Data Index: 5948112 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1950. Min Act: -0.1700

Data Index: 1410984 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1913. Min Act: -0.1700

Data Index: 6749916 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1915. Min Act: -0.1691

Data Index: 6355337 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1813. Min Act: -0.1700

Data Index: 7979857 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1828. Min Act: -0.1697

Data Index: 7058131 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1792. Min Act: -0.1700

Data Index: 2037138 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1860. Min Act: -0.1700

Data Index: 5898439 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1716. Min Act: -0.1700

Data Index: 5993573 (Open Web Text)

Max Activating Token Index: 149

Text #12

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1752. Min Act: -0.1699

Data Index: 2093028 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1801. Min Act: -0.1697

Data Index: 6489183 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1758. Min Act: -0.1698

Data Index: 1152587 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1662. Min Act: -0.1699

Data Index: 3848846 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1693. Min Act: -0.1695

Data Index: 1126225 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1633. Min Act: -0.1699

Data Index: 4939724 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1684. Min Act: -0.1700

Data Index: 2055592 (Open Web Text)

Max Activating Token Index: 65

Text #19

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1737. Min Act: -0.1698

Data Index: 6785289 (Open Web Text)

Max Activating Token Index: 791