Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.3847. Min Act: -0.1700
Data Index: 3119645 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.2909. Min Act: -0.1700
Data Index: 7071656 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.3222. Min Act: -0.1700
Data Index: 8181565 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.1347. Min Act: -0.1700
Data Index: 504437 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.1347. Min Act: -0.1700
Data Index: 6801445 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.1347. Min Act: -0.1700
Data Index: 7077141 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.0096. Min Act: -0.1700
Data Index: 4085520 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.0096. Min Act: -0.1700
Data Index: 3328750 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.0096. Min Act: -0.1700
Data Index: 3524791 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.0096. Min Act: -0.1700
Data Index: 3580753 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3847. Min Range: -4.3847
Max Act: 4.0409. Min Act: -0.1700
Data Index: 7941922 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.9471. Min Act: -0.1700
Data Index: 3126786 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.9784. Min Act: -0.1700
Data Index: 374782 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.9784. Min Act: -0.1700
Data Index: 6322448 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.9158. Min Act: -0.1700
Data Index: 5756751 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.8846. Min Act: -0.1700
Data Index: 4646716 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.8846. Min Act: -0.1700
Data Index: 8510947 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.9471. Min Act: -0.1700
Data Index: 4345923 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.8846. Min Act: -0.1700
Data Index: 348949 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3847. Min Range: -4.3847
Max Act: 3.8846. Min Act: -0.1700
Data Index: 3678060 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19