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

Dataset: Open Web Text

Neuron 826 in Layer 2

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: 1.7294. Min Range: -1.7294

Max Act: 1.7294. Min Act: -0.1700

Data Index: 2004488 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7166. Min Act: -0.1700

Data Index: 8235588 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7219. Min Act: -0.1700

Data Index: 8323774 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7163. Min Act: -0.1700

Data Index: 8741081 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7099. Min Act: -0.1700

Data Index: 7952776 (Open Web Text)

Max Activating Token Index: 1008

Text #5

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6846. Min Act: -0.1700

Data Index: 6148444 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6795. Min Act: -0.1700

Data Index: 4443299 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6609. Min Act: -0.1700

Data Index: 4844866 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6553. Min Act: -0.1700

Data Index: 96187 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6647. Min Act: -0.1700

Data Index: 6938195 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6558. Min Act: -0.1700

Data Index: 7787895 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6506. Min Act: -0.1700

Data Index: 4936927 (Open Web Text)

Max Activating Token Index: 628

Text #12

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6541. Min Act: -0.1700

Data Index: 7415371 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6472. Min Act: -0.1700

Data Index: 5744870 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6508. Min Act: -0.1700

Data Index: 6977739 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6529. Min Act: -0.1700

Data Index: 3311991 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6531. Min Act: -0.1700

Data Index: 6530636 (Open Web Text)

Max Activating Token Index: 363

Text #17

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6406. Min Act: -0.1700

Data Index: 2568201 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6479. Min Act: -0.1700

Data Index: 1218123 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6582. Min Act: -0.1700

Data Index: 7918619 (Open Web Text)

Max Activating Token Index: 943