Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.6773. Min Act: -0.1700
Data Index: 6590083 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.6773. Min Act: -0.1700
Data Index: 5947504 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.6461. Min Act: -0.1700
Data Index: 2283599 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 4374717 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 749546 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 8681178 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 5255987 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 4840522 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5836. Min Act: -0.1700
Data Index: 5947508 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 7357558 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5523. Min Act: -0.1699
Data Index: 2103919 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5523. Min Act: -0.1700
Data Index: 749547 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5463815 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 7127026 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 4967107 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 746169 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 5630000 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 3448417 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 7750408 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6773. Min Range: -4.6773
Max Act: 4.5211. Min Act: -0.1700
Data Index: 6590081 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19