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

Dataset: Open Web Text

Neuron 1779 in Layer 2

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: 3.3295. Min Range: -3.3295

Max Act: 3.3295. Min Act: -0.1700

Data Index: 2466595 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.3024. Min Act: -0.1700

Data Index: 6264267 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.2642. Min Act: -0.1700

Data Index: 7667091 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.2024. Min Act: -0.1700

Data Index: 5252506 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1813. Min Act: -0.1700

Data Index: 146703 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1735. Min Act: -0.1700

Data Index: 2146106 (Open Web Text)

Max Activating Token Index: 750

Text #6

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1657. Min Act: -0.1700

Data Index: 5135698 (Open Web Text)

Max Activating Token Index: 216

Text #7

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1758. Min Act: -0.1700

Data Index: 6576831 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1784351 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1523. Min Act: -0.1700

Data Index: 4457278 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1416. Min Act: -0.1700

Data Index: 8505859 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1380. Min Act: -0.1700

Data Index: 4094846 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1423. Min Act: -0.1700

Data Index: 3702534 (Open Web Text)

Max Activating Token Index: 439

Text #13

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1110. Min Act: -0.1700

Data Index: 6576823 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1291. Min Act: -0.1700

Data Index: 403477 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1033. Min Act: -0.1700

Data Index: 2280233 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1199. Min Act: -0.1700

Data Index: 1292588 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1179. Min Act: -0.1700

Data Index: 8040903 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.1005. Min Act: -0.1700

Data Index: 1769983 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 3.3295. Min Range: -3.3295

Max Act: 3.0767. Min Act: -0.1700

Data Index: 4904678 (Open Web Text)

Max Activating Token Index: 683