Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.9379. Min Act: -0.1700
Data Index: 3357244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.9379. Min Act: -0.1700
Data Index: 5957046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.9062. Min Act: -0.1700
Data Index: 5352612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.9062. Min Act: -0.1700
Data Index: 6941252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3488570 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3694132 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 2574010 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3545690 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 4946099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3541441 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 1325960 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 1311136 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3421986 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3359144 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 4764063 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 4615905 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 4598656 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3255043 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3163558 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9379. Min Range: -2.9379
Max Act: 2.8744. Min Act: -0.1700
Data Index: 2134200 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19