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

Dataset: Open Web Text

Neuron 1121 in Layer 4

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: 4.0323. Min Range: -4.0323

Max Act: 4.0323. Min Act: -0.1700

Data Index: 632982 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 4.0323. Min Range: -4.0323

Max Act: 4.0323. Min Act: -0.1700

Data Index: 5382869 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 4.0323. Min Range: -4.0323

Max Act: 4.0138. Min Act: -0.1700

Data Index: 895723 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 4.0323. Min Range: -4.0323

Max Act: 4.0290. Min Act: -0.1700

Data Index: 120940 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 4.0323. Min Range: -4.0323

Max Act: 4.0130. Min Act: -0.1700

Data Index: 1647930 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9885. Min Act: -0.1700

Data Index: 7984569 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9899. Min Act: -0.1700

Data Index: 4461326 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9656. Min Act: -0.1700

Data Index: 1815353 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9338. Min Act: -0.1700

Data Index: 1112454 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9313. Min Act: -0.1700

Data Index: 7418007 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9525. Min Act: -0.1700

Data Index: 4948778 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9770. Min Act: -0.1700

Data Index: 4910117 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9335. Min Act: -0.1700

Data Index: 2725578 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9241. Min Act: -0.1700

Data Index: 1261993 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9199. Min Act: -0.1700

Data Index: 1860132 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9026. Min Act: -0.1700

Data Index: 4789323 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9099. Min Act: -0.1700

Data Index: 1732838 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9207. Min Act: -0.1700

Data Index: 4446636 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9196. Min Act: -0.1700

Data Index: 1651898 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 4.0323. Min Range: -4.0323

Max Act: 3.9132. Min Act: -0.1700

Data Index: 2491288 (Open Web Text)

Max Activating Token Index: 705