Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0644. Min Act: -0.1700
Data Index: 5810856 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0644. Min Act: -0.1700
Data Index: 238248 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 8656364 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 257942 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 501792 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 1409539 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 3917173 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0644. Min Act: -0.1700
Data Index: 1270899 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 3369277 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 8149299 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 2207806 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 2148725 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 359009 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0644. Min Range: -6.0644
Max Act: 5.9707. Min Act: -0.1700
Data Index: 3754041 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0644. Min Range: -6.0644
Max Act: 5.9707. Min Act: -0.1700
Data Index: 1486775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 5158755 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0332. Min Act: -0.1700
Data Index: 4125615 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 5148996 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 4486936 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0644. Min Range: -6.0644
Max Act: 6.0019. Min Act: -0.1700
Data Index: 7479001 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19