Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.6551. Min Act: -0.1700
Data Index: 543063 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.5926. Min Act: -0.1700
Data Index: 543062 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.5614. Min Act: -0.1700
Data Index: 2281189 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.5614. Min Act: -0.1700
Data Index: 8057716 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.5301. Min Act: -0.1700
Data Index: 3436778 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4989. Min Act: -0.1700
Data Index: 5294910 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 4096795 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 6910263 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 5984331 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 1584122 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 634344 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4364. Min Act: -0.1700
Data Index: 3668748 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3055806 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4051. Min Act: -0.1700
Data Index: 7037534 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4051. Min Act: -0.1700
Data Index: 7393175 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4051. Min Act: -0.1700
Data Index: 8484143 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.4051. Min Act: -0.1700
Data Index: 242841 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.3739. Min Act: -0.1700
Data Index: 3880215 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.3739. Min Act: -0.1700
Data Index: 4156193 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6551. Min Range: -5.6551
Max Act: 5.3739. Min Act: -0.1700
Data Index: 5208564 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19