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

Dataset: Open Web Text

Neuron 1560 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: 3.3285. Min Range: -3.3285

Max Act: 3.3285. Min Act: -0.1700

Data Index: 1453622 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2419. Min Act: -0.1700

Data Index: 4200873 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.2163. Min Act: -0.1700

Data Index: 6963002 (Open Web Text)

Max Activating Token Index: 419

Text #3

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1720. Min Act: -0.1700

Data Index: 846865 (Open Web Text)

Max Activating Token Index: 206

Text #4

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1797. Min Act: -0.1700

Data Index: 6698720 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1928. Min Act: -0.1700

Data Index: 2725612 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1414. Min Act: -0.1700

Data Index: 7053048 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1741. Min Act: -0.1700

Data Index: 7451889 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1252. Min Act: -0.1700

Data Index: 6252316 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1141. Min Act: -0.1700

Data Index: 3575536 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1295521 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0883. Min Act: -0.1700

Data Index: 8056201 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1095. Min Act: -0.1700

Data Index: 8208543 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1588. Min Act: -0.1700

Data Index: 955028 (Open Web Text)

Max Activating Token Index: 726

Text #14

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0947. Min Act: -0.1700

Data Index: 2953456 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1318. Min Act: -0.1700

Data Index: 5079655 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1282. Min Act: -0.1700

Data Index: 6983488 (Open Web Text)

Max Activating Token Index: 258

Text #17

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0920. Min Act: -0.1700

Data Index: 5983836 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1025. Min Act: -0.1700

Data Index: 3440009 (Open Web Text)

Max Activating Token Index: 273

Text #19

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1176. Min Act: -0.1700

Data Index: 1697510 (Open Web Text)

Max Activating Token Index: 525