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

Dataset: Open Web Text

Neuron 888 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: 4.3262. Min Range: -4.3262

Max Act: 4.3262. Min Act: -0.1700

Data Index: 1422136 (Open Web Text)

Max Activating Token Index: 405

Text #1

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.3118. Min Act: -0.1700

Data Index: 6810878 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.2475. Min Act: -0.1700

Data Index: 7166826 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.2118. Min Act: -0.1700

Data Index: 5560613 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.2108. Min Act: -0.1700

Data Index: 4192197 (Open Web Text)

Max Activating Token Index: 451

Text #5

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1937. Min Act: -0.1700

Data Index: 2195644 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1892. Min Act: -0.1700

Data Index: 2843847 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1771. Min Act: -0.1700

Data Index: 3211073 (Open Web Text)

Max Activating Token Index: 581

Text #8

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1576. Min Act: -0.1700

Data Index: 5620751 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1597. Min Act: -0.1700

Data Index: 6647814 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1117. Min Act: -0.1700

Data Index: 2143716 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1093. Min Act: -0.1700

Data Index: 4018671 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1273. Min Act: -0.1700

Data Index: 845822 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1187. Min Act: -0.1700

Data Index: 3397543 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1144. Min Act: -0.1700

Data Index: 1560266 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1038. Min Act: -0.1700

Data Index: 506428 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.1122. Min Act: -0.1700

Data Index: 6811319 (Open Web Text)

Max Activating Token Index: 348

Text #17

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.0950. Min Act: -0.1700

Data Index: 25901 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.0777. Min Act: -0.1700

Data Index: 1023439 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.3262. Min Range: -4.3262

Max Act: 4.0950. Min Act: -0.1700

Data Index: 603956 (Open Web Text)

Max Activating Token Index: 200