Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1594. Min Range: -5.1594
Max Act: 5.1594. Min Act: -0.1700
Data Index: 6982255 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1594. Min Range: -5.1594
Max Act: 5.1594. Min Act: -0.1700
Data Index: 2293231 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1594. Min Range: -5.1594
Max Act: 5.0656. Min Act: -0.1700
Data Index: 4239711 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1594. Min Range: -5.1594
Max Act: 5.0031. Min Act: -0.1700
Data Index: 2094774 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.9719. Min Act: -0.1700
Data Index: 3609426 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.9719. Min Act: -0.1700
Data Index: 7948843 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.9406. Min Act: -0.1700
Data Index: 5454740 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.9406. Min Act: -0.1700
Data Index: 2764189 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.9094. Min Act: -0.1700
Data Index: 3609427 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8781. Min Act: -0.1700
Data Index: 3853007 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 531761 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 4230028 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 605782 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 2626492 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 7936281 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8469. Min Act: -0.1700
Data Index: 7936112 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 2916160 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 7678732 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 7607568 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1594. Min Range: -5.1594
Max Act: 4.8156. Min Act: -0.1700
Data Index: 7069707 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19