Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5557 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.1256. Min Act: -0.1700
Data Index: 8774751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 5733851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 3552583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 5848038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 7979949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 6246499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 7624835 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 4303310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0626. Min Act: -0.1700
Data Index: 7586804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 1129804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 7938616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 3182390 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 4649962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 2592625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 145502 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 3899526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 2288892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 6924814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 6273809 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1256. Min Range: -3.1256
Max Act: 3.0152. Min Act: -0.1700
Data Index: 575270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19