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

Dataset: Open Web Text

Neuron 806 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: 3.0080. Min Range: -3.0080

Max Act: 3.0080. Min Act: -0.1700

Data Index: 1224236 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.9007. Min Act: -0.1700

Data Index: 1764420 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8209. Min Act: -0.1700

Data Index: 3560541 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8050. Min Act: -0.1700

Data Index: 5412211 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8110. Min Act: -0.1700

Data Index: 1122739 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7892. Min Act: -0.1700

Data Index: 5799762 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7953. Min Act: -0.1700

Data Index: 1563136 (Open Web Text)

Max Activating Token Index: 251

Text #7

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.8062. Min Act: -0.1700

Data Index: 2795347 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7789. Min Act: -0.1700

Data Index: 6089847 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7884. Min Act: -0.1700

Data Index: 4004865 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7735. Min Act: -0.1700

Data Index: 206179 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7741. Min Act: -0.1700

Data Index: 4430533 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7855. Min Act: -0.1700

Data Index: 2429288 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7698. Min Act: -0.1700

Data Index: 3207100 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7464. Min Act: -0.1700

Data Index: 3670896 (Open Web Text)

Max Activating Token Index: 736

Text #15

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7616. Min Act: -0.1700

Data Index: 3221995 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7555. Min Act: -0.1700

Data Index: 7225291 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7612. Min Act: -0.1700

Data Index: 447259 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7444. Min Act: -0.1700

Data Index: 491746 (Open Web Text)

Max Activating Token Index: 785

Text #19

Max Range: 3.0080. Min Range: -3.0080

Max Act: 2.7682. Min Act: -0.1700

Data Index: 3175194 (Open Web Text)

Max Activating Token Index: 766