Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8958. Min Act: -0.1700
Data Index: 8277404 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8646. Min Act: -0.1700
Data Index: 6255595 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1033325 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 968628 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 6620421 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8021. Min Act: -0.1700
Data Index: 4250170 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8021. Min Act: -0.1700
Data Index: 1917403 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7708. Min Act: -0.1700
Data Index: 1671888 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7396. Min Act: -0.1700
Data Index: 8001981 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7396. Min Act: -0.1700
Data Index: 8472908 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 1666674 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 622171 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 1199454 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 6604183 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6458. Min Act: -0.1700
Data Index: 1999579 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5341308 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5950229 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.5521. Min Act: -0.1700
Data Index: 5999290 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.5833. Min Act: -0.1700
Data Index: 3527565 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4340391 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19