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

Dataset: Open Web Text

Neuron 1822 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: 1.2169. Min Range: -1.2169

Max Act: 1.2169. Min Act: -0.1541

Data Index: 8271469 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1985. Min Act: -0.1682

Data Index: 5313578 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1707. Min Act: -0.1655

Data Index: 2487276 (Open Web Text)

Max Activating Token Index: 871

Text #3

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1618. Min Act: -0.1629

Data Index: 1892020 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1418. Min Act: -0.1576

Data Index: 7446421 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1450. Min Act: -0.1628

Data Index: 6248480 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1349. Min Act: -0.1699

Data Index: 4784018 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1306. Min Act: -0.1678

Data Index: 8683753 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1373. Min Act: -0.1636

Data Index: 4564756 (Open Web Text)

Max Activating Token Index: 214

Text #9

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1302. Min Act: -0.1634

Data Index: 628778 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1251. Min Act: -0.1515

Data Index: 31736 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1263. Min Act: -0.1669

Data Index: 2924696 (Open Web Text)

Max Activating Token Index: 908

Text #12

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1313. Min Act: -0.1660

Data Index: 6455119 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1108. Min Act: -0.1569

Data Index: 1340619 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1159. Min Act: -0.1665

Data Index: 4715104 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1173. Min Act: -0.1548

Data Index: 2266320 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1120. Min Act: -0.1688

Data Index: 7123362 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1131. Min Act: -0.1584

Data Index: 752100 (Open Web Text)

Max Activating Token Index: 1018

Text #18

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1164. Min Act: -0.1615

Data Index: 3463653 (Open Web Text)

Max Activating Token Index: 998

Text #19

Max Range: 1.2169. Min Range: -1.2169

Max Act: 1.1158. Min Act: -0.1671

Data Index: 5656742 (Open Web Text)

Max Activating Token Index: 637