Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1325 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0199. Min Range: -6.0199
Max Act: 6.0199. Min Act: -0.1700
Data Index: 1963411 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.9887. Min Act: -0.1700
Data Index: 7813273 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.9262. Min Act: -0.1700
Data Index: 5181600 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8949. Min Act: -0.1700
Data Index: 7201855 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8949. Min Act: -0.1700
Data Index: 3918690 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8324. Min Act: -0.1700
Data Index: 1442366 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3603801 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8012. Min Act: -0.1700
Data Index: 8313963 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8012. Min Act: -0.1700
Data Index: 213516 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8012. Min Act: -0.1700
Data Index: 6796162 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7387. Min Act: -0.1700
Data Index: 568068 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7699. Min Act: -0.1700
Data Index: 811110 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7699. Min Act: -0.1700
Data Index: 719387 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6449. Min Act: -0.1700
Data Index: 8626054 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6449. Min Act: -0.1700
Data Index: 3539742 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6449. Min Act: -0.1700
Data Index: 33158 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6137. Min Act: -0.1700
Data Index: 1952626 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6137. Min Act: -0.1700
Data Index: 4488483 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6137. Min Act: -0.1700
Data Index: 8200276 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6137. Min Act: -0.1700
Data Index: 3554073 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19