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

Dataset: Open Web Text

Neuron 168 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: 3.7933. Min Range: -3.7933

Max Act: 3.7871. Min Act: -0.1700

Data Index: 294077 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7933. Min Act: -0.1700

Data Index: 2797995 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7630. Min Act: -0.1700

Data Index: 8317240 (Open Web Text)

Max Activating Token Index: 814

Text #3

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7343. Min Act: -0.1700

Data Index: 3968794 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7482. Min Act: -0.1700

Data Index: 439356 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7207. Min Act: -0.1700

Data Index: 1811757 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6982. Min Act: -0.1700

Data Index: 6815656 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7168. Min Act: -0.1700

Data Index: 697169 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7066. Min Act: -0.1700

Data Index: 177592 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1168230 (Open Web Text)

Max Activating Token Index: 951

Text #10

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7213. Min Act: -0.1700

Data Index: 4945231 (Open Web Text)

Max Activating Token Index: 722

Text #11

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7252. Min Act: -0.1700

Data Index: 5613623 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6782. Min Act: -0.1700

Data Index: 3182082 (Open Web Text)

Max Activating Token Index: 891

Text #13

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.7030. Min Act: -0.1700

Data Index: 7289723 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6617. Min Act: -0.1700

Data Index: 5663346 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6592. Min Act: -0.1700

Data Index: 5372891 (Open Web Text)

Max Activating Token Index: 994

Text #16

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6578. Min Act: -0.1700

Data Index: 8582325 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6716. Min Act: -0.1700

Data Index: 6764172 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6495. Min Act: -0.1700

Data Index: 5732167 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 3.7933. Min Range: -3.7933

Max Act: 3.6463. Min Act: -0.1700

Data Index: 3750644 (Open Web Text)

Max Activating Token Index: 114