Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1072. Min Range: -6.1072
Max Act: 6.1072. Min Act: -0.1700
Data Index: 2601122 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1072. Min Range: -6.1072
Max Act: 6.0447. Min Act: -0.1700
Data Index: 1730364 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1072. Min Range: -6.1072
Max Act: 6.0134. Min Act: -0.1700
Data Index: 3121900 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9822. Min Act: -0.1698
Data Index: 1566268 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9822. Min Act: -0.1700
Data Index: 8475413 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9509. Min Act: -0.1700
Data Index: 166239 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9822. Min Act: -0.1700
Data Index: 4318164 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9509. Min Act: -0.1700
Data Index: 6849357 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9822. Min Act: -0.1696
Data Index: 4899190 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.9197. Min Act: -0.1700
Data Index: 7162453 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7463875 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3268289 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8884. Min Act: -0.1700
Data Index: 5895521 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8884. Min Act: -0.1700
Data Index: 5444990 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3423536 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3060725 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8572. Min Act: -0.1700
Data Index: 387079 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.7947. Min Act: -0.1700
Data Index: 4629115 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3607927 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1072. Min Range: -6.1072
Max Act: 5.8259. Min Act: -0.1700
Data Index: 351327 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19