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

Dataset: Open Web Text

Neuron 64 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: 4.0471. Min Range: -4.0471

Max Act: 4.0471. Min Act: -0.1700

Data Index: 3344283 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9922. Min Act: -0.1700

Data Index: 768071 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9951. Min Act: -0.1700

Data Index: 4846992 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9010. Min Act: -0.1700

Data Index: 8513049 (Open Web Text)

Max Activating Token Index: 766

Text #4

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9102. Min Act: -0.1700

Data Index: 6108240 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9417. Min Act: -0.1700

Data Index: 97625 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9377. Min Act: -0.1700

Data Index: 2341131 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9935. Min Act: -0.1700

Data Index: 6895867 (Open Web Text)

Max Activating Token Index: 429

Text #8

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9800. Min Act: -0.1700

Data Index: 7226082 (Open Web Text)

Max Activating Token Index: 931

Text #9

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9739. Min Act: -0.1700

Data Index: 568982 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9093. Min Act: -0.1700

Data Index: 2256177 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.8773. Min Act: -0.1700

Data Index: 4336597 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9215. Min Act: -0.1700

Data Index: 1065717 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9274. Min Act: -0.1700

Data Index: 2906234 (Open Web Text)

Max Activating Token Index: 530

Text #14

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.8949. Min Act: -0.1700

Data Index: 7763671 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9240. Min Act: -0.1700

Data Index: 6859080 (Open Web Text)

Max Activating Token Index: 292

Text #16

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9674. Min Act: -0.1700

Data Index: 3407464 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.9204. Min Act: -0.1700

Data Index: 2245422 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.8697. Min Act: -0.1700

Data Index: 4479743 (Open Web Text)

Max Activating Token Index: 952

Text #19

Max Range: 4.0471. Min Range: -4.0471

Max Act: 3.8880. Min Act: -0.1700

Data Index: 5493627 (Open Web Text)

Max Activating Token Index: 377