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

Dataset: Open Web Text

Neuron 2783 in Layer 0

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: 2.8259. Min Range: -2.8259

Max Act: 2.8259. Min Act: -0.1700

Data Index: 4416421 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7907. Min Act: -0.1700

Data Index: 3152945 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7844. Min Act: -0.1700

Data Index: 4359279 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7994. Min Act: -0.1700

Data Index: 3831472 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7840. Min Act: -0.1700

Data Index: 5028665 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7915. Min Act: -0.1700

Data Index: 479191 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 6537694 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 2691444 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7711. Min Act: -0.1700

Data Index: 5536825 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7814. Min Act: -0.1700

Data Index: 8700121 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 586616 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 8113852 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 2148520 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7773. Min Act: -0.1700

Data Index: 471324 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7778. Min Act: -0.1700

Data Index: 286649 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 1857822 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7742. Min Act: -0.1700

Data Index: 7857576 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7778. Min Act: -0.1700

Data Index: 4999797 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 7459821 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8259. Min Range: -2.8259

Max Act: 2.7832. Min Act: -0.1700

Data Index: 381646 (Open Web Text)

Max Activating Token Index: 2