Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.9055. Min Act: -0.1700
Data Index: 174097 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.5930. Min Act: -0.1700
Data Index: 7437534 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.5305. Min Act: -0.1700
Data Index: 7515205 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.5305. Min Act: -0.1700
Data Index: 5150013 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.3430. Min Act: -0.1700
Data Index: 2702576 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2805. Min Act: -0.1700
Data Index: 3491166 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2180. Min Act: -0.1700
Data Index: 2339184 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2180. Min Act: -0.1700
Data Index: 3670261 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2180. Min Act: -0.1700
Data Index: 6225940 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2180. Min Act: -0.1700
Data Index: 1889669 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.2180. Min Act: -0.1700
Data Index: 4226829 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.1555. Min Act: -0.1700
Data Index: 7535214 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.0930. Min Act: -0.1700
Data Index: 5129076 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.1555. Min Act: -0.1700
Data Index: 4305921 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.1555. Min Act: -0.1700
Data Index: 8483015 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.1555. Min Act: -0.1700
Data Index: 8163786 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.1555. Min Act: -0.1700
Data Index: 6901064 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.0930. Min Act: -0.1700
Data Index: 1071491 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.0930. Min Act: -0.1700
Data Index: 1899126 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9055. Min Range: -8.9055
Max Act: 8.0930. Min Act: -0.1700
Data Index: 6061809 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19