Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.6848. Min Act: -0.1700
Data Index: 5876513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.6045. Min Act: -0.1700
Data Index: 6908650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5884. Min Act: -0.1700
Data Index: 1090026 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5884. Min Act: -0.1700
Data Index: 8421295 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5562. Min Act: -0.1700
Data Index: 8642451 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5723. Min Act: -0.1700
Data Index: 7983196 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5562. Min Act: -0.1700
Data Index: 1092904 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5562. Min Act: -0.1700
Data Index: 784019 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5562. Min Act: -0.1700
Data Index: 7928096 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 1307829 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5229135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 144060 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 8057080 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 4532467 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5591018 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5239. Min Act: -0.1700
Data Index: 6512318 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 4034032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5401. Min Act: -0.1700
Data Index: 3197901 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5239. Min Act: -0.1700
Data Index: 589067 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6848. Min Range: -2.6848
Max Act: 2.5239. Min Act: -0.1700
Data Index: 2104690 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19