Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.2962. Min Act: -0.1700
Data Index: 1649742 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.2337. Min Act: -0.1700
Data Index: 644349 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.2024. Min Act: -0.1700
Data Index: 8351290 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.1399. Min Act: -0.1700
Data Index: 3834967 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0774. Min Act: -0.1700
Data Index: 8394469 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0774. Min Act: -0.1700
Data Index: 512057 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0462. Min Act: -0.1700
Data Index: 6615218 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0149. Min Act: -0.1700
Data Index: 7065313 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0149. Min Act: -0.1700
Data Index: 1409287 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 4879949 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 8224755 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 2787569 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 7414011 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0149. Min Act: -0.1700
Data Index: 2328325 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 52720 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 6951213 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2962. Min Range: -6.2962
Max Act: 6.0149. Min Act: -0.1700
Data Index: 2562366 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9524. Min Act: -0.1700
Data Index: 4745405 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 6620394 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2962. Min Range: -6.2962
Max Act: 5.9837. Min Act: -0.1700
Data Index: 5845717 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19