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

Dataset: Open Web Text

Neuron 398 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: 3.7924. Min Range: -3.7924

Max Act: 3.7924. Min Act: -0.1700

Data Index: 5229942 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6460. Min Act: -0.1700

Data Index: 6638517 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6017. Min Act: -0.1700

Data Index: 3186043 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5484. Min Act: -0.1700

Data Index: 6646738 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6010. Min Act: -0.1700

Data Index: 6912962 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5401. Min Act: -0.1700

Data Index: 2353710 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5547. Min Act: -0.1700

Data Index: 2450653 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5512. Min Act: -0.1700

Data Index: 6571385 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5617. Min Act: -0.1700

Data Index: 8306488 (Open Web Text)

Max Activating Token Index: 897

Text #9

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5129. Min Act: -0.1700

Data Index: 2788677 (Open Web Text)

Max Activating Token Index: 128

Text #10

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5034. Min Act: -0.1700

Data Index: 7474604 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5080. Min Act: -0.1700

Data Index: 7932458 (Open Web Text)

Max Activating Token Index: 909

Text #12

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5035. Min Act: -0.1700

Data Index: 34130 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4804. Min Act: -0.1700

Data Index: 4385217 (Open Web Text)

Max Activating Token Index: 408

Text #14

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4797. Min Act: -0.1700

Data Index: 2106251 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4877. Min Act: -0.1700

Data Index: 994684 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4595. Min Act: -0.1700

Data Index: 3696437 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4863. Min Act: -0.1700

Data Index: 4597701 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4800. Min Act: -0.1700

Data Index: 8819948 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4744. Min Act: -0.1700

Data Index: 3392022 (Open Web Text)

Max Activating Token Index: 902