Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0766. Min Range: -6.0766
Max Act: 6.0766. Min Act: -0.1700
Data Index: 7706474 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.5454. Min Act: -0.1700
Data Index: 1572095 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 5365929 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.3579. Min Act: -0.1700
Data Index: 4858462 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.3579. Min Act: -0.1700
Data Index: 4213807 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2954. Min Act: -0.1700
Data Index: 7902482 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2954. Min Act: -0.1700
Data Index: 3658084 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2329. Min Act: -0.1700
Data Index: 5070657 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2016. Min Act: -0.1700
Data Index: 5861774 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2329. Min Act: -0.1700
Data Index: 6412744 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2969309 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4802971 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2016. Min Act: -0.1700
Data Index: 3792512 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2016. Min Act: -0.1700
Data Index: 5272627 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.2016. Min Act: -0.1700
Data Index: 5019505 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1391. Min Act: -0.1700
Data Index: 7499461 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4418132 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1704. Min Act: -0.1700
Data Index: 3492617 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3421878 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0766. Min Range: -6.0766
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3125298 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19