Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.2698. Min Act: -0.1700
Data Index: 7645655 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.1136. Min Act: -0.1700
Data Index: 2236241 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.1136. Min Act: -0.1700
Data Index: 5891689 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.0511. Min Act: -0.1700
Data Index: 8008902 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.0198. Min Act: -0.1700
Data Index: 5659659 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2698. Min Range: -6.2698
Max Act: 6.0198. Min Act: -0.1700
Data Index: 1703052 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.9886. Min Act: -0.1700
Data Index: 363735 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.9573. Min Act: -0.1700
Data Index: 4271893 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.9573. Min Act: -0.1700
Data Index: 5711090 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.9261. Min Act: -0.1700
Data Index: 6470675 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.8636. Min Act: -0.1700
Data Index: 11021 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.8636. Min Act: -0.1700
Data Index: 4804775 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.8636. Min Act: -0.1700
Data Index: 8180276 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.8323. Min Act: -0.1700
Data Index: 8017234 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.8011. Min Act: -0.1700
Data Index: 5539225 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.7698. Min Act: -0.1700
Data Index: 4654182 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.7698. Min Act: -0.1700
Data Index: 7960013 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.7698. Min Act: -0.1700
Data Index: 7663408 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2450608 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2698. Min Range: -6.2698
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2776268 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19