Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.5557. Min Act: -0.1700
Data Index: 8655949 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4932. Min Act: -0.1700
Data Index: 6579698 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4932. Min Act: -0.1700
Data Index: 6684219 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 582960 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 1328166 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 6867825 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 2437753 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 7528732 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 6419587 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 6295308 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 4105437 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3057. Min Act: -0.1700
Data Index: 1687756 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.3057. Min Act: -0.1700
Data Index: 3032644 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.2432. Min Act: -0.1700
Data Index: 5350815 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.2432. Min Act: -0.1700
Data Index: 2649782 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 6443762 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 3321372 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 8211998 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 4834038 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5557. Min Range: -8.5557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 8450909 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19