Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5324 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.9345. Min Act: -0.1700
Data Index: 2832703 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.5595. Min Act: -0.1700
Data Index: 8258865 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.4970. Min Act: -0.1700
Data Index: 210663 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.3720. Min Act: -0.1700
Data Index: 8191704 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.4345. Min Act: -0.1700
Data Index: 3505387 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.3720. Min Act: -0.1699
Data Index: 2042848 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.3720. Min Act: -0.1700
Data Index: 4922763 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 705423 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.3095. Min Act: -0.1700
Data Index: 3997463 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.3095. Min Act: -0.1700
Data Index: 5109086 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 1995775 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 705422 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 6929783 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.1845. Min Act: -0.1699
Data Index: 7083826 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.2470. Min Act: -0.1700
Data Index: 7254141 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.1220. Min Act: -0.1700
Data Index: 7256332 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.0595. Min Act: -0.1700
Data Index: 6090760 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.1220. Min Act: -0.1700
Data Index: 3895710 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9345. Min Range: -8.9345
Max Act: 8.0595. Min Act: -0.1700
Data Index: 1934822 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9345. Min Range: -8.9345
Max Act: 7.9970. Min Act: -0.1700
Data Index: 8410722 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19