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

Dataset: Open Web Text

Neuron 552 in Layer 3

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: 4.1304. Min Range: -4.1304

Max Act: 4.1304. Min Act: -0.1700

Data Index: 2066396 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0708. Min Act: -0.1700

Data Index: 8174751 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0357. Min Act: -0.1700

Data Index: 5091965 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0101. Min Act: -0.1700

Data Index: 4515617 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0385. Min Act: -0.1700

Data Index: 7659711 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0215. Min Act: -0.1700

Data Index: 472511 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0180. Min Act: -0.1700

Data Index: 8642302 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0594. Min Act: -0.1700

Data Index: 3034253 (Open Web Text)

Max Activating Token Index: 363

Text #8

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0117. Min Act: -0.1700

Data Index: 4103703 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9889. Min Act: -0.1700

Data Index: 465464 (Open Web Text)

Max Activating Token Index: 832

Text #10

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0140. Min Act: -0.1700

Data Index: 4352588 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0213. Min Act: -0.1700

Data Index: 3976510 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9458. Min Act: -0.1700

Data Index: 7314055 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9746. Min Act: -0.1700

Data Index: 3959833 (Open Web Text)

Max Activating Token Index: 427

Text #14

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9543. Min Act: -0.1700

Data Index: 5460943 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9747. Min Act: -0.1700

Data Index: 2488711 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9335. Min Act: -0.1700

Data Index: 8400444 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 4.1304. Min Range: -4.1304

Max Act: 4.0198. Min Act: -0.1700

Data Index: 1247287 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9550. Min Act: -0.1700

Data Index: 4034801 (Open Web Text)

Max Activating Token Index: 701

Text #19

Max Range: 4.1304. Min Range: -4.1304

Max Act: 3.9265. Min Act: -0.1700

Data Index: 4910090 (Open Web Text)

Max Activating Token Index: 496