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

Dataset: Open Web Text

Neuron 1836 in Layer 5

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: 4.2762. Min Range: -4.2762

Max Act: 4.2762. Min Act: -0.1700

Data Index: 6642850 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2489. Min Act: -0.1700

Data Index: 6937291 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2397. Min Act: -0.1700

Data Index: 6522455 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.2132. Min Act: -0.1700

Data Index: 5501718 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1779. Min Act: -0.1700

Data Index: 2802268 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1997. Min Act: -0.1700

Data Index: 8742499 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1808. Min Act: -0.1700

Data Index: 91135 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1823. Min Act: -0.1700

Data Index: 1852066 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1606. Min Act: -0.1700

Data Index: 7609129 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1266. Min Act: -0.1700

Data Index: 5727896 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1525. Min Act: -0.1700

Data Index: 296541 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1432. Min Act: -0.1700

Data Index: 7473153 (Open Web Text)

Max Activating Token Index: 941

Text #12

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1391. Min Act: -0.1700

Data Index: 6678614 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1270. Min Act: -0.1700

Data Index: 507551 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1214. Min Act: -0.1700

Data Index: 4780012 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1664. Min Act: -0.1700

Data Index: 4545545 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1177. Min Act: -0.1700

Data Index: 6167857 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1296. Min Act: -0.1700

Data Index: 2851014 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1059. Min Act: -0.1700

Data Index: 5122871 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 4.2762. Min Range: -4.2762

Max Act: 4.1048. Min Act: -0.1700

Data Index: 5353718 (Open Web Text)

Max Activating Token Index: 714