Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.2100. Min Act: -0.1700
Data Index: 7608325 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1475. Min Act: -0.1700
Data Index: 7915867 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1475. Min Act: -0.1700
Data Index: 457174 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 515746 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 1173918 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 5232760 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 1965604 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 6844585 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 1592842 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 4880080 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 7796913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 4157656 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 4094452 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.1162. Min Act: -0.1700
Data Index: 2666626 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 408683 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 5274181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0850. Min Act: -0.1700
Data Index: 1425135 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0537. Min Act: -0.1700
Data Index: 3085455 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0537. Min Act: -0.1700
Data Index: 3199680 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2100. Min Range: -4.2100
Max Act: 4.0537. Min Act: -0.1700
Data Index: 5368961 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19