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

Dataset: Open Web Text

Neuron 2949 in Layer 0

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: 1.6956. Min Range: -1.6956

Max Act: 1.6956. Min Act: -0.1698

Data Index: 2687388 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6659. Min Act: -0.1700

Data Index: 7818078 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6759. Min Act: -0.1697

Data Index: 8053270 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6457. Min Act: -0.1699

Data Index: 1832784 (Open Web Text)

Max Activating Token Index: 360

Text #4

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6503. Min Act: -0.1700

Data Index: 927843 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6475. Min Act: -0.1697

Data Index: 2842493 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6461. Min Act: -0.1700

Data Index: 1745406 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6452. Min Act: -0.1700

Data Index: 3469200 (Open Web Text)

Max Activating Token Index: 370

Text #8

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6380. Min Act: -0.1699

Data Index: 1466694 (Open Web Text)

Max Activating Token Index: 1001

Text #9

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6298. Min Act: -0.1626

Data Index: 1132093 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6399. Min Act: -0.1700

Data Index: 4877429 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6287. Min Act: -0.1700

Data Index: 63303 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6312. Min Act: -0.1699

Data Index: 3832891 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6209. Min Act: -0.1692

Data Index: 1845578 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6287. Min Act: -0.1695

Data Index: 6860252 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6155. Min Act: -0.1700

Data Index: 1271993 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6235. Min Act: -0.1699

Data Index: 482320 (Open Web Text)

Max Activating Token Index: 665

Text #17

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6201. Min Act: -0.1695

Data Index: 2273759 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6285. Min Act: -0.1699

Data Index: 7901123 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6270. Min Act: -0.1699

Data Index: 5594686 (Open Web Text)

Max Activating Token Index: 735