Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.1698. Min Act: -0.1700
Data Index: 1772187 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.1073. Min Act: -0.1700
Data Index: 7083258 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.1073. Min Act: -0.1700
Data Index: 1575163 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.1386. Min Act: -0.1700
Data Index: 4773628 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.0761. Min Act: -0.1700
Data Index: 2942370 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.0136. Min Act: -0.1700
Data Index: 5257630 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9823. Min Act: -0.1700
Data Index: 3361901 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1698. Min Range: -8.1698
Max Act: 8.0136. Min Act: -0.1700
Data Index: 1180155 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9511. Min Act: -0.1700
Data Index: 5662628 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9511. Min Act: -0.1700
Data Index: 3273709 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9511. Min Act: -0.1700
Data Index: 3621130 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9198. Min Act: -0.1700
Data Index: 5950982 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9198. Min Act: -0.1700
Data Index: 5787462 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.9198. Min Act: -0.1700
Data Index: 3057157 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.8573. Min Act: -0.1700
Data Index: 5338232 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.8886. Min Act: -0.1700
Data Index: 7155236 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.8261. Min Act: -0.1700
Data Index: 5532877 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.8261. Min Act: -0.1700
Data Index: 794262 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.8261. Min Act: -0.1700
Data Index: 3369854 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1698. Min Range: -8.1698
Max Act: 7.7948. Min Act: -0.1700
Data Index: 1999482 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19