Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5680 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1090. Min Range: -5.1090
Max Act: 5.1090. Min Act: -0.1700
Data Index: 6457418 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1090. Min Range: -5.1090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4642463 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1090. Min Range: -5.1090
Max Act: 5.0777. Min Act: -0.1700
Data Index: 1474028 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1090. Min Range: -5.1090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 7065980 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1090. Min Range: -5.1090
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5430067 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9840. Min Act: -0.1700
Data Index: 8589377 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9840. Min Act: -0.1700
Data Index: 2055803 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9840. Min Act: -0.1700
Data Index: 805599 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9840. Min Act: -0.1700
Data Index: 1478791 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9527. Min Act: -0.1700
Data Index: 2406993 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9527. Min Act: -0.1700
Data Index: 763400 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9215. Min Act: -0.1700
Data Index: 6645746 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.9215. Min Act: -0.1700
Data Index: 4736149 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8902. Min Act: -0.1700
Data Index: 8078672 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8902. Min Act: -0.1700
Data Index: 606511 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8902. Min Act: -0.1700
Data Index: 6371830 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8590. Min Act: -0.1700
Data Index: 429527 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8902. Min Act: -0.1700
Data Index: 5755558 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8590. Min Act: -0.1700
Data Index: 1378544 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1090. Min Range: -5.1090
Max Act: 4.8590. Min Act: -0.1700
Data Index: 4950275 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19