Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.8006. Min Act: -0.1700
Data Index: 988233 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.6756. Min Act: -0.1700
Data Index: 6006811 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.6131. Min Act: -0.1700
Data Index: 2173710 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.5506. Min Act: -0.1700
Data Index: 6568767 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.4881. Min Act: -0.1700
Data Index: 198756 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.4881. Min Act: -0.1700
Data Index: 560877 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.4256. Min Act: -0.1700
Data Index: 264064 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.4256. Min Act: -0.1700
Data Index: 2911203 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 2606002 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3631. Min Act: -0.1700
Data Index: 2644868 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 7580490 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 4696579 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 7334692 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 7049246 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 2478236 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.3006. Min Act: -0.1700
Data Index: 8488222 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.2381. Min Act: -0.1700
Data Index: 3089064 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.2381. Min Act: -0.1700
Data Index: 803046 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.2381. Min Act: -0.1700
Data Index: 1123936 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8006. Min Range: -8.8006
Max Act: 8.1756. Min Act: -0.1700
Data Index: 3712373 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19