Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.5138. Min Act: -0.1700
Data Index: 7995939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4513. Min Act: -0.1700
Data Index: 5355284 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4201. Min Act: -0.1700
Data Index: 1316119 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4201. Min Act: -0.1700
Data Index: 7863048 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7648840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4201. Min Act: -0.1700
Data Index: 6680088 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.4201. Min Act: -0.1700
Data Index: 3255423 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3888. Min Act: -0.1700
Data Index: 3865839 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3888. Min Act: -0.1700
Data Index: 4845006 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3888. Min Act: -0.1700
Data Index: 7056669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3888. Min Act: -0.1700
Data Index: 5758039 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3888. Min Act: -0.1700
Data Index: 2819462 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 1746988 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 1963115 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5609378 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5610944 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 2606291 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5833513 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5836956 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5138. Min Range: -6.5138
Max Act: 6.3576. Min Act: -0.1700
Data Index: 6110551 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19