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

Dataset: Open Web Text

Neuron 1397 in Layer 5

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: 3.8767. Min Range: -3.8767

Max Act: 3.8646. Min Act: -0.1700

Data Index: 4244524 (Open Web Text)

Max Activating Token Index: 913

Text #1

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.8767. Min Act: -0.1700

Data Index: 4142500 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.8002. Min Act: -0.1700

Data Index: 6818522 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.7136. Min Act: -0.1700

Data Index: 5362513 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.7085. Min Act: -0.1700

Data Index: 1088363 (Open Web Text)

Max Activating Token Index: 509

Text #5

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5921. Min Act: -0.1700

Data Index: 8659147 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.6236. Min Act: -0.1700

Data Index: 6938555 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5642. Min Act: -0.1700

Data Index: 8029463 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.6012. Min Act: -0.1700

Data Index: 6056176 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5358. Min Act: -0.1700

Data Index: 6059906 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5860. Min Act: -0.1700

Data Index: 7656090 (Open Web Text)

Max Activating Token Index: 893

Text #11

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5498. Min Act: -0.1700

Data Index: 6056186 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5156. Min Act: -0.1700

Data Index: 1745225 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5483. Min Act: -0.1700

Data Index: 2415941 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5247. Min Act: -0.1700

Data Index: 7146027 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1535266 (Open Web Text)

Max Activating Token Index: 445

Text #16

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5216. Min Act: -0.1700

Data Index: 5503995 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5212. Min Act: -0.1700

Data Index: 366680 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5017. Min Act: -0.1700

Data Index: 2071126 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 3.8767. Min Range: -3.8767

Max Act: 3.5118. Min Act: -0.1700

Data Index: 7659799 (Open Web Text)

Max Activating Token Index: 791