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

Dataset: Open Web Text

Neuron 770 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: 5.3343. Min Range: -5.3343

Max Act: 5.3343. Min Act: -0.1700

Data Index: 5199179 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.3132. Min Act: -0.1700

Data Index: 210445 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2666. Min Act: -0.1700

Data Index: 3533954 (Open Web Text)

Max Activating Token Index: 418

Text #3

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2324. Min Act: -0.1700

Data Index: 3178616 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2962. Min Act: -0.1700

Data Index: 2651904 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2730. Min Act: -0.1700

Data Index: 4495071 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2681. Min Act: -0.1700

Data Index: 2556000 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1928. Min Act: -0.1700

Data Index: 6354642 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2361. Min Act: -0.1700

Data Index: 4053471 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2331. Min Act: -0.1700

Data Index: 7109846 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2307. Min Act: -0.1700

Data Index: 3009848 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1947. Min Act: -0.1700

Data Index: 139057 (Open Web Text)

Max Activating Token Index: 849

Text #12

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2391. Min Act: -0.1700

Data Index: 3517357 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.2127. Min Act: -0.1700

Data Index: 8345080 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1664. Min Act: -0.1700

Data Index: 2146339 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1762. Min Act: -0.1700

Data Index: 8164696 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1874. Min Act: -0.1700

Data Index: 7035959 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1793. Min Act: -0.1700

Data Index: 7958514 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1546. Min Act: -0.1700

Data Index: 1467968 (Open Web Text)

Max Activating Token Index: 472

Text #19

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1696. Min Act: -0.1700

Data Index: 8132835 (Open Web Text)

Max Activating Token Index: 393