Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 4027856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 6053906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 7733499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 7663279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 7216120 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 2638938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 1537158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9948. Min Act: -0.1700
Data Index: 6643485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9323. Min Act: -0.1700
Data Index: 2167282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9323. Min Act: -0.1700
Data Index: 1585391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9011. Min Act: -0.1700
Data Index: 1669038 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9323. Min Act: -0.1700
Data Index: 1692599 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9011. Min Act: -0.1700
Data Index: 4373864 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9011. Min Act: -0.1700
Data Index: 1516091 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.9323. Min Act: -0.1700
Data Index: 8663973 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 1132348 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5256644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 862705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 6052731 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9948. Min Range: -4.9948
Max Act: 4.8698. Min Act: -0.1700
Data Index: 3776107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19