Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6735244 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3997542 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9528. Min Act: -0.1700
Data Index: 5960557 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9840. Min Act: -0.1700
Data Index: 795807 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9215. Min Act: -0.1700
Data Index: 1503224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9215. Min Act: -0.1700
Data Index: 1354672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9215. Min Act: -0.1700
Data Index: 4965632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.9215. Min Act: -0.1700
Data Index: 3633073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8903. Min Act: -0.1700
Data Index: 388258 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8590. Min Act: -0.1700
Data Index: 3068339 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8590. Min Act: -0.1700
Data Index: 233499 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 3956105 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8590. Min Act: -0.1700
Data Index: 3392336 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.7965. Min Act: -0.1700
Data Index: 5044998 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 62463 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 6538219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 19171 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 2912823 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.7965. Min Act: -0.1700
Data Index: 2873477 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9840. Min Range: -4.9840
Max Act: 4.8278. Min Act: -0.1700
Data Index: 648322 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19