Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.1661. Min Act: -0.1700
Data Index: 31901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.1349. Min Act: -0.1700
Data Index: 1537227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.1036. Min Act: -0.1700
Data Index: 3935300 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0724. Min Act: -0.1700
Data Index: 2905612 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0724. Min Act: -0.1700
Data Index: 7328669 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0724. Min Act: -0.1700
Data Index: 5516573 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0411. Min Act: -0.1700
Data Index: 3327430 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0411. Min Act: -0.1700
Data Index: 3660563 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0411. Min Act: -0.1700
Data Index: 6032211 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0411. Min Act: -0.1700
Data Index: 4930475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0411. Min Act: -0.1700
Data Index: 7344096 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 6467454 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 1506950 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 6154871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 8410151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 72487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 4646530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 4130475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 6722593 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1661. Min Range: -4.1661
Max Act: 4.0099. Min Act: -0.1700
Data Index: 2330877 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19