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

Dataset: Open Web Text

Neuron 2901 in Layer 6

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: 3.4617. Min Range: -3.4617

Max Act: 3.4617. Min Act: -0.1700

Data Index: 8399959 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.4009. Min Act: -0.1700

Data Index: 616044 (Open Web Text)

Max Activating Token Index: 818

Text #2

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.3531. Min Act: -0.1700

Data Index: 274890 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.3411. Min Act: -0.1700

Data Index: 5912850 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1727706 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1522060 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.3152. Min Act: -0.1700

Data Index: 1093523 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2761. Min Act: -0.1700

Data Index: 8481577 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2976. Min Act: -0.1700

Data Index: 5528991 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2849. Min Act: -0.1700

Data Index: 5893488 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2789. Min Act: -0.1700

Data Index: 3046324 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2507. Min Act: -0.1700

Data Index: 7242666 (Open Web Text)

Max Activating Token Index: 822

Text #12

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1767054 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2672. Min Act: -0.1700

Data Index: 4584823 (Open Web Text)

Max Activating Token Index: 800

Text #14

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2453. Min Act: -0.1700

Data Index: 6720360 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2520. Min Act: -0.1700

Data Index: 7612760 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2766. Min Act: -0.1700

Data Index: 612266 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2819. Min Act: -0.1700

Data Index: 6904886 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2266. Min Act: -0.1700

Data Index: 3691658 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 3.4617. Min Range: -3.4617

Max Act: 3.2399. Min Act: -0.1700

Data Index: 5355196 (Open Web Text)

Max Activating Token Index: 143