Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4743 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.5447. Min Act: -0.1700
Data Index: 3068839 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.5134. Min Act: -0.1700
Data Index: 2993104 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2099013 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2634. Min Act: -0.1700
Data Index: 3020086 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2947. Min Act: -0.1700
Data Index: 1509255 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2634. Min Act: -0.1700
Data Index: 1022478 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2634. Min Act: -0.1700
Data Index: 7410188 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2322. Min Act: -0.1700
Data Index: 8720981 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2009. Min Act: -0.1700
Data Index: 4833705 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 5072159 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2009. Min Act: -0.1700
Data Index: 1735250 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.2009. Min Act: -0.1700
Data Index: 8776250 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 5308732 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 7429093 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 4766971 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 5979221 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 4259152 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 1452954 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 4948297 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5447. Min Range: -5.5447
Max Act: 5.1697. Min Act: -0.1700
Data Index: 242114 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19