Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4153 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.5388. Min Range: -15.5388
Max Act: 15.5388. Min Act: -0.1699
Data Index: 2188072 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.5388. Min Range: -15.5388
Max Act: 15.2888. Min Act: -0.1700
Data Index: 5292778 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.5388. Min Range: -15.5388
Max Act: 15.1638. Min Act: -0.1700
Data Index: 4103387 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.5388. Min Range: -15.5388
Max Act: 15.1013. Min Act: -0.1697
Data Index: 2188092 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.6638. Min Act: -0.1700
Data Index: 4441966 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.5388. Min Act: -0.1700
Data Index: 4103373 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.5388. Min Act: -0.1700
Data Index: 5040169 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.0388. Min Act: -0.1696
Data Index: 8003991 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.1013. Min Act: -0.1700
Data Index: 2188090 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.5388. Min Range: -15.5388
Max Act: 14.0388. Min Act: -0.1700
Data Index: 7591658 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.9763. Min Act: -0.1700
Data Index: 4103390 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.9763. Min Act: -0.1700
Data Index: 2188073 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.9138. Min Act: -0.1700
Data Index: 2188080 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.9763. Min Act: -0.1700
Data Index: 4441970 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.8513. Min Act: -0.1700
Data Index: 5040172 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.8513. Min Act: -0.1700
Data Index: 8173795 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.8513. Min Act: -0.1700
Data Index: 5395838 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.8513. Min Act: -0.1700
Data Index: 4441968 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.7888. Min Act: -0.1700
Data Index: 5040167 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.5388. Min Range: -15.5388
Max Act: 13.7263. Min Act: -0.1696
Data Index: 6398673 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19