Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2781. Min Range: -9.2781
Max Act: 9.2781. Min Act: -0.1700
Data Index: 7724135 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2781. Min Range: -9.2781
Max Act: 9.2781. Min Act: -0.1700
Data Index: 1209200 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2781. Min Range: -9.2781
Max Act: 9.1531. Min Act: -0.1700
Data Index: 6883223 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2781. Min Range: -9.2781
Max Act: 9.0906. Min Act: -0.1700
Data Index: 8069449 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2781. Min Range: -9.2781
Max Act: 9.0281. Min Act: -0.1700
Data Index: 6659566 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.9656. Min Act: -0.1700
Data Index: 8530267 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.9031. Min Act: -0.1700
Data Index: 183895 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.9031. Min Act: -0.1700
Data Index: 2974345 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7781. Min Act: -0.1700
Data Index: 5934249 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7156. Min Act: -0.1700
Data Index: 6885209 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7781. Min Act: -0.1700
Data Index: 587275 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7781. Min Act: -0.1700
Data Index: 8035184 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7156. Min Act: -0.1700
Data Index: 1604518 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.7781. Min Act: -0.1699
Data Index: 852429 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.6531. Min Act: -0.1700
Data Index: 5481744 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.6531. Min Act: -0.1700
Data Index: 576742 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.6531. Min Act: -0.1700
Data Index: 4994691 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.5906. Min Act: -0.1700
Data Index: 3386337 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.5906. Min Act: -0.1700
Data Index: 5696673 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2781. Min Range: -9.2781
Max Act: 8.5906. Min Act: -0.1700
Data Index: 3758950 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19