Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.5880. Min Act: -0.1700
Data Index: 3932778 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.5530. Min Act: -0.1700
Data Index: 7273411 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.5355. Min Act: -0.1700
Data Index: 2646449 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4828. Min Act: -0.1700
Data Index: 8136500 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4653. Min Act: -0.1700
Data Index: 6707631 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4477. Min Act: -0.1700
Data Index: 2118250 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 7775560 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 2053757 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 381666 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 557598 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 7444492 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4477. Min Act: -0.1700
Data Index: 7470455 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 7876599 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.3948. Min Act: -0.1700
Data Index: 1596585 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4125. Min Act: -0.1700
Data Index: 3008025 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4125. Min Act: -0.1700
Data Index: 6132815 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4125. Min Act: -0.1700
Data Index: 3837925 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4301. Min Act: -0.1700
Data Index: 1360914 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4125. Min Act: -0.1700
Data Index: 8407019 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5880. Min Range: -1.5880
Max Act: 1.4125. Min Act: -0.1700
Data Index: 8582452 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19