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

Dataset: Open Web Text

Neuron 1852 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: 2.1775. Min Range: -2.1775

Max Act: 2.1775. Min Act: -0.1700

Data Index: 1260366 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1507. Min Act: -0.1700

Data Index: 4850531 (Open Web Text)

Max Activating Token Index: 344

Text #2

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1366. Min Act: -0.1700

Data Index: 3960413 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1243. Min Act: -0.1700

Data Index: 5841219 (Open Web Text)

Max Activating Token Index: 417

Text #4

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1102. Min Act: -0.1700

Data Index: 1307312 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1121. Min Act: -0.1700

Data Index: 864555 (Open Web Text)

Max Activating Token Index: 297

Text #6

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1042. Min Act: -0.1700

Data Index: 6146590 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1123. Min Act: -0.1700

Data Index: 8481798 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0987. Min Act: -0.1700

Data Index: 3460201 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1212. Min Act: -0.1700

Data Index: 7798520 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0855. Min Act: -0.1700

Data Index: 7902445 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1124. Min Act: -0.1700

Data Index: 5409335 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0671. Min Act: -0.1700

Data Index: 7254786 (Open Web Text)

Max Activating Token Index: 414

Text #13

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0909. Min Act: -0.1700

Data Index: 291686 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0917. Min Act: -0.1700

Data Index: 7585692 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0423. Min Act: -0.1700

Data Index: 3729412 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1153. Min Act: -0.1700

Data Index: 7857420 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0948. Min Act: -0.1700

Data Index: 4768293 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0560. Min Act: -0.1700

Data Index: 7380624 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.0787. Min Act: -0.1700

Data Index: 7900598 (Open Web Text)

Max Activating Token Index: 409