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

Dataset: Open Web Text

Neuron 76 in Layer 1

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: 1.2976. Min Range: -1.2976

Max Act: 1.2976. Min Act: -0.1664

Data Index: 3663656 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.2713. Min Act: -0.1649

Data Index: 5003333 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1800. Min Act: -0.1661

Data Index: 6602349 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1716. Min Act: -0.1699

Data Index: 1888359 (Open Web Text)

Max Activating Token Index: 151

Text #4

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1605. Min Act: -0.1700

Data Index: 6286040 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1463. Min Act: -0.1658

Data Index: 2574568 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1376. Min Act: -0.1700

Data Index: 8613172 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1456. Min Act: -0.1555

Data Index: 7313355 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1428. Min Act: -0.1473

Data Index: 2126901 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1304. Min Act: -0.1677

Data Index: 6682025 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1395. Min Act: -0.1700

Data Index: 7136374 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1279. Min Act: -0.1700

Data Index: 3338567 (Open Web Text)

Max Activating Token Index: 743

Text #12

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1197. Min Act: -0.1696

Data Index: 3982199 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1228. Min Act: -0.1700

Data Index: 8050940 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1233. Min Act: -0.1647

Data Index: 8122284 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1242. Min Act: -0.1697

Data Index: 7259902 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1284. Min Act: -0.1700

Data Index: 5853796 (Open Web Text)

Max Activating Token Index: 915

Text #17

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1123. Min Act: -0.1699

Data Index: 4839745 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1251. Min Act: -0.1698

Data Index: 4936185 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1272. Min Act: -0.1620

Data Index: 8284601 (Open Web Text)

Max Activating Token Index: 763