Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 228 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.8722. Min Act: -0.1700
Data Index: 8097754 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.6222. Min Act: -0.1700
Data Index: 1333981 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.5597. Min Act: -0.1700
Data Index: 3166063 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.5597. Min Act: -0.1700
Data Index: 8208856 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4972. Min Act: -0.1700
Data Index: 2672844 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4972. Min Act: -0.1700
Data Index: 2425357 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4347. Min Act: -0.1700
Data Index: 6979419 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4972. Min Act: -0.1700
Data Index: 8352915 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4347. Min Act: -0.1700
Data Index: 6654467 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.4347. Min Act: -0.1700
Data Index: 4979585 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.3722. Min Act: -0.1700
Data Index: 4689112 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.3722. Min Act: -0.1700
Data Index: 3420012 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.3097. Min Act: -0.1700
Data Index: 53158 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.3097. Min Act: -0.1700
Data Index: 1624732 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.2472. Min Act: -0.1700
Data Index: 6917977 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.2472. Min Act: -0.1700
Data Index: 773776 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.2472. Min Act: -0.1700
Data Index: 229905 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.1534. Min Act: -0.1700
Data Index: 5048462 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.1222. Min Act: -0.1700
Data Index: 1799932 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8722. Min Range: -8.8722
Max Act: 8.1847. Min Act: -0.1700
Data Index: 753837 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19