Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 986 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.4259. Min Act: -0.1700
Data Index: 6584863 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.4259. Min Act: -0.1700
Data Index: 3604192 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.4259. Min Act: -0.1700
Data Index: 4058403 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.4259. Min Act: -0.1700
Data Index: 1009747 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.4259. Min Act: -0.1700
Data Index: 8214238 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3634. Min Act: -0.1700
Data Index: 376486 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3634. Min Act: -0.1700
Data Index: 711386 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3009. Min Act: -0.1700
Data Index: 1389819 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3009. Min Act: -0.1700
Data Index: 3170648 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3009. Min Act: -0.1700
Data Index: 3710161 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3634. Min Act: -0.1700
Data Index: 7476891 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 6622724 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 5543961 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 8383961 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 217027 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 7158189 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.3009. Min Act: -0.1700
Data Index: 7018911 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 2819706 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.2384. Min Act: -0.1700
Data Index: 931327 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4259. Min Range: -8.4259
Max Act: 8.1759. Min Act: -0.1700
Data Index: 5631311 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19