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

Dataset: Open Web Text

Neuron 1530 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: 1.8800. Min Range: -1.8800

Max Act: 1.8800. Min Act: -0.1503

Data Index: 7283044 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8581. Min Act: -0.1698

Data Index: 3508705 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8386. Min Act: -0.1700

Data Index: 6607952 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8318. Min Act: -0.1697

Data Index: 2782873 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8300. Min Act: -0.1700

Data Index: 3797295 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8221. Min Act: -0.1700

Data Index: 6895697 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8320. Min Act: -0.1700

Data Index: 1788843 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8151. Min Act: -0.1432

Data Index: 3250520 (Open Web Text)

Max Activating Token Index: 312

Text #8

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8177. Min Act: -0.1700

Data Index: 3532987 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8258. Min Act: -0.1696

Data Index: 5229714 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8128. Min Act: -0.1655

Data Index: 710143 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8109. Min Act: -0.1700

Data Index: 8198048 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8049. Min Act: -0.1644

Data Index: 841058 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7970. Min Act: -0.1694

Data Index: 3156581 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7952. Min Act: -0.1700

Data Index: 6272933 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8091. Min Act: -0.1689

Data Index: 1221899 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8043. Min Act: -0.1700

Data Index: 3546758 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8063. Min Act: -0.1680

Data Index: 7562015 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8042. Min Act: -0.1671

Data Index: 5136451 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8038. Min Act: -0.1700

Data Index: 3609119 (Open Web Text)

Max Activating Token Index: 12