Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1434 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.9073. Min Act: -0.1700
Data Index: 3903566 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.4073. Min Act: -0.1700
Data Index: 3576103 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.3448. Min Act: -0.1700
Data Index: 1206634 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.2823. Min Act: -0.1700
Data Index: 3903567 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.2198. Min Act: -0.1700
Data Index: 3705669 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.1573. Min Act: -0.1700
Data Index: 8808008 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.1573. Min Act: -0.1700
Data Index: 6419429 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.1573. Min Act: -0.1700
Data Index: 3903565 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0948. Min Act: -0.1700
Data Index: 4834772 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0948. Min Act: -0.1700
Data Index: 1206633 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 4090814 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 1363848 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 3903564 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 8096885 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 1942889 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9073. Min Range: -8.9073
Max Act: 8.0323. Min Act: -0.1700
Data Index: 4834777 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9073. Min Range: -8.9073
Max Act: 7.9698. Min Act: -0.1700
Data Index: 1403863 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9073. Min Range: -8.9073
Max Act: 7.9698. Min Act: -0.1700
Data Index: 7964579 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9073. Min Range: -8.9073
Max Act: 7.9698. Min Act: -0.1700
Data Index: 1403845 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9073. Min Range: -8.9073
Max Act: 7.9698. Min Act: -0.1700
Data Index: 785956 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19