Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.6002. Min Act: -0.1700
Data Index: 3325604 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4752. Min Act: -0.1700
Data Index: 184862 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4752. Min Act: -0.1700
Data Index: 5509585 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4752. Min Act: -0.1700
Data Index: 5404891 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4440. Min Act: -0.1700
Data Index: 7302563 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4127. Min Act: -0.1700
Data Index: 59389 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.4127. Min Act: -0.1700
Data Index: 6793649 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3815. Min Act: -0.1700
Data Index: 5313996 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3502. Min Act: -0.1700
Data Index: 1599131 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3815. Min Act: -0.1700
Data Index: 2122390 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3815. Min Act: -0.1700
Data Index: 893542 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3502. Min Act: -0.1700
Data Index: 1388169 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3502. Min Act: -0.1700
Data Index: 5367601 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.2877. Min Act: -0.1700
Data Index: 6736125 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3190. Min Act: -0.1700
Data Index: 2878218 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3190. Min Act: -0.1700
Data Index: 5524130 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.2877. Min Act: -0.1700
Data Index: 5651119 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3190. Min Act: -0.1700
Data Index: 7459932 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.2565. Min Act: -0.1700
Data Index: 4875199 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6002. Min Range: -4.6002
Max Act: 4.3190. Min Act: -0.1700
Data Index: 2241948 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19