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

Dataset: Open Web Text

Neuron 130 in Layer 3

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: 4.2814. Min Range: -4.2814

Max Act: 4.2814. Min Act: -0.1700

Data Index: 4953262 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 4.2814. Min Range: -4.2814

Max Act: 4.2081. Min Act: -0.1700

Data Index: 4166855 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.2814. Min Range: -4.2814

Max Act: 4.0455. Min Act: -0.1700

Data Index: 1111013 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 4.2814. Min Range: -4.2814

Max Act: 4.0141. Min Act: -0.1700

Data Index: 4706346 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 4.2814. Min Range: -4.2814

Max Act: 4.0023. Min Act: -0.1700

Data Index: 6713271 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9982. Min Act: -0.1700

Data Index: 56811 (Open Web Text)

Max Activating Token Index: 968

Text #6

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9746. Min Act: -0.1700

Data Index: 2199785 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9507. Min Act: -0.1700

Data Index: 6469783 (Open Web Text)

Max Activating Token Index: 385

Text #8

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9731. Min Act: -0.1700

Data Index: 5170530 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9798. Min Act: -0.1700

Data Index: 5685969 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9514. Min Act: -0.1700

Data Index: 3874907 (Open Web Text)

Max Activating Token Index: 968

Text #11

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9696. Min Act: -0.1700

Data Index: 7819667 (Open Web Text)

Max Activating Token Index: 690

Text #12

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9555. Min Act: -0.1700

Data Index: 1503116 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9420. Min Act: -0.1700

Data Index: 4570122 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9055. Min Act: -0.1700

Data Index: 638892 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9372. Min Act: -0.1700

Data Index: 5217844 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9199. Min Act: -0.1700

Data Index: 894013 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9345. Min Act: -0.1700

Data Index: 3900627 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9046. Min Act: -0.1700

Data Index: 6127001 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 4.2814. Min Range: -4.2814

Max Act: 3.9016. Min Act: -0.1700

Data Index: 2102093 (Open Web Text)

Max Activating Token Index: 346