Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1087. Min Range: -6.1087
Max Act: 6.1087. Min Act: -0.1700
Data Index: 8585937 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.9525. Min Act: -0.1700
Data Index: 5780217 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.9212. Min Act: -0.1700
Data Index: 2594953 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.7962. Min Act: -0.1700
Data Index: 256972 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3124845 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.7025. Min Act: -0.1700
Data Index: 2139407 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.7025. Min Act: -0.1700
Data Index: 8560211 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6712. Min Act: -0.1700
Data Index: 3530141 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6400. Min Act: -0.1700
Data Index: 1473438 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6712. Min Act: -0.1700
Data Index: 3858646 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 2983427 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6794580 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6400. Min Act: -0.1700
Data Index: 5467965 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 5613409 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 1614180 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.5775. Min Act: -0.1700
Data Index: 3361105 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.5775. Min Act: -0.1700
Data Index: 2694907 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3068739 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6400. Min Act: -0.1700
Data Index: 8472257 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1087. Min Range: -6.1087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 505259 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19