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

Dataset: Open Web Text

Neuron 1399 in Layer 1

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: 4.8126. Min Range: -4.8126

Max Act: 4.8126. Min Act: -0.1700

Data Index: 5051762 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.7094. Min Act: -0.1700

Data Index: 6295294 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.7155. Min Act: -0.1700

Data Index: 2902043 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6855. Min Act: -0.1700

Data Index: 3569181 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6785. Min Act: -0.1700

Data Index: 3488664 (Open Web Text)

Max Activating Token Index: 476

Text #5

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6875. Min Act: -0.1700

Data Index: 5048471 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6546. Min Act: -0.1700

Data Index: 1961982 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6764. Min Act: -0.1700

Data Index: 5193701 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6651. Min Act: -0.1700

Data Index: 7173588 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6617. Min Act: -0.1700

Data Index: 2645974 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6612. Min Act: -0.1700

Data Index: 294087 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6312. Min Act: -0.1700

Data Index: 7675588 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6247. Min Act: -0.1700

Data Index: 3452048 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6348. Min Act: -0.1700

Data Index: 7063088 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6431. Min Act: -0.1700

Data Index: 4124699 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6235. Min Act: -0.1700

Data Index: 5518826 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6626. Min Act: -0.1700

Data Index: 595484 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6485. Min Act: -0.1700

Data Index: 4512732 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6470. Min Act: -0.1700

Data Index: 985645 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 4.8126. Min Range: -4.8126

Max Act: 4.6400. Min Act: -0.1700

Data Index: 4437481 (Open Web Text)

Max Activating Token Index: 620