Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.9666. Min Act: -0.1700
Data Index: 5819222 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.9979. Min Act: -0.1700
Data Index: 276398 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8729. Min Act: -0.1700
Data Index: 3204920 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8729. Min Act: -0.1700
Data Index: 6771662 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8729. Min Act: -0.1700
Data Index: 5906102 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8729. Min Act: -0.1700
Data Index: 688709 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8416. Min Act: -0.1700
Data Index: 5906098 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8416. Min Act: -0.1700
Data Index: 1721963 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8416. Min Act: -0.1700
Data Index: 688716 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8416. Min Act: -0.1700
Data Index: 7769410 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8104. Min Act: -0.1700
Data Index: 5906101 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4339219 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8104. Min Act: -0.1700
Data Index: 1969092 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.8104. Min Act: -0.1700
Data Index: 2680945 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 625715 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4776899 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 3847791 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5906106 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 645608 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9979. Min Range: -5.9979
Max Act: 5.7791. Min Act: -0.1700
Data Index: 8327107 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19