Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1635. Min Range: -6.1635
Max Act: 6.1635. Min Act: -0.1700
Data Index: 5746296 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.8510. Min Act: -0.1700
Data Index: 5574283 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.8198. Min Act: -0.1700
Data Index: 3019604 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.7885. Min Act: -0.1700
Data Index: 5746289 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6948. Min Act: -0.1700
Data Index: 1162607 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1847748 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6948. Min Act: -0.1700
Data Index: 3844729 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6948. Min Act: -0.1700
Data Index: 6752983 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6635. Min Act: -0.1700
Data Index: 5609216 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3486173 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1064862 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6323. Min Act: -0.1700
Data Index: 2931271 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6323. Min Act: -0.1700
Data Index: 3775011 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5561776 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5746295 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 2115160 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5422404 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 2772705 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 4707032 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1635. Min Range: -6.1635
Max Act: 5.6010. Min Act: -0.1700
Data Index: 3390413 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19