Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1836. Min Range: -7.1836
Max Act: 7.1836. Min Act: -0.1700
Data Index: 8010547 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1836. Min Range: -7.1836
Max Act: 7.0586. Min Act: -0.1700
Data Index: 2050 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1836. Min Range: -7.1836
Max Act: 7.0898. Min Act: -0.1700
Data Index: 6284807 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.9961. Min Act: -0.1700
Data Index: 7004985 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1836. Min Range: -7.1836
Max Act: 7.0273. Min Act: -0.1700
Data Index: 1975167 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.9648. Min Act: -0.1700
Data Index: 5314321 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.9023. Min Act: -0.1700
Data Index: 195403 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.9648. Min Act: -0.1700
Data Index: 7960582 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.8398. Min Act: -0.1700
Data Index: 6885949 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.8398. Min Act: -0.1700
Data Index: 3125950 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.8086. Min Act: -0.1700
Data Index: 5973095 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7461. Min Act: -0.1700
Data Index: 2546678 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7773. Min Act: -0.1700
Data Index: 2833661 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7773. Min Act: -0.1700
Data Index: 8115239 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7461. Min Act: -0.1700
Data Index: 7155230 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.6836. Min Act: -0.1700
Data Index: 3813007 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1592502 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7773. Min Act: -0.1700
Data Index: 6089522 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.7461. Min Act: -0.1700
Data Index: 1324624 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1836. Min Range: -7.1836
Max Act: 6.6836. Min Act: -0.1700
Data Index: 1570225 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19