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

Dataset: Open Web Text

Neuron 1995 in Layer 2

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: 1.9180. Min Range: -1.9180

Max Act: 1.9180. Min Act: -0.1700

Data Index: 4942571 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.9103. Min Act: -0.1700

Data Index: 1619484 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.9010. Min Act: -0.1700

Data Index: 3315841 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.9087. Min Act: -0.1700

Data Index: 6207102 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.9058. Min Act: -0.1700

Data Index: 1481234 (Open Web Text)

Max Activating Token Index: 651

Text #5

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8855. Min Act: -0.1700

Data Index: 6523795 (Open Web Text)

Max Activating Token Index: 637

Text #6

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8936. Min Act: -0.1700

Data Index: 8229973 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8883. Min Act: -0.1700

Data Index: 8714945 (Open Web Text)

Max Activating Token Index: 899

Text #8

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8676. Min Act: -0.1700

Data Index: 1480931 (Open Web Text)

Max Activating Token Index: 691

Text #9

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8693. Min Act: -0.1700

Data Index: 3989776 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8510. Min Act: -0.1700

Data Index: 67353 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8543. Min Act: -0.1700

Data Index: 1603681 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8334. Min Act: -0.1700

Data Index: 5536830 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8455. Min Act: -0.1700

Data Index: 1508439 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8437. Min Act: -0.1700

Data Index: 4987828 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8306. Min Act: -0.1700

Data Index: 2834221 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8365. Min Act: -0.1700

Data Index: 4128754 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8350. Min Act: -0.1700

Data Index: 3603478 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8369. Min Act: -0.1700

Data Index: 2771693 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 1.9180. Min Range: -1.9180

Max Act: 1.8315. Min Act: -0.1700

Data Index: 621699 (Open Web Text)

Max Activating Token Index: 366