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

Dataset: Open Web Text

Neuron 1391 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: 3.2336. Min Range: -3.2336

Max Act: 3.2336. Min Act: -0.1700

Data Index: 5916386 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1801. Min Act: -0.1700

Data Index: 6525234 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1746. Min Act: -0.1700

Data Index: 7827607 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1069003 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1452. Min Act: -0.1700

Data Index: 8559807 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1453. Min Act: -0.1700

Data Index: 3032079 (Open Web Text)

Max Activating Token Index: 114

Text #6

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1117002 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1337. Min Act: -0.1700

Data Index: 7407656 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1265. Min Act: -0.1700

Data Index: 2979571 (Open Web Text)

Max Activating Token Index: 997

Text #9

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1285. Min Act: -0.1700

Data Index: 2107161 (Open Web Text)

Max Activating Token Index: 436

Text #10

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1271. Min Act: -0.1700

Data Index: 5633248 (Open Web Text)

Max Activating Token Index: 903

Text #11

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1224. Min Act: -0.1700

Data Index: 8266167 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1185. Min Act: -0.1700

Data Index: 4999206 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1028. Min Act: -0.1700

Data Index: 194907 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1063. Min Act: -0.1700

Data Index: 2804343 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1143. Min Act: -0.1700

Data Index: 4888990 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.0910. Min Act: -0.1700

Data Index: 7843050 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.0999. Min Act: -0.1700

Data Index: 4483327 (Open Web Text)

Max Activating Token Index: 849

Text #18

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.0907. Min Act: -0.1700

Data Index: 6324647 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.2336. Min Range: -3.2336

Max Act: 3.1075. Min Act: -0.1700

Data Index: 5679236 (Open Web Text)

Max Activating Token Index: 412