Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.3807. Min Act: -0.1700
Data Index: 4571882 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 7608930 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.1619. Min Act: -0.1700
Data Index: 4560936 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0994. Min Act: -0.1700
Data Index: 753509 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0994. Min Act: -0.1700
Data Index: 5225120 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0994. Min Act: -0.1700
Data Index: 2552557 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0682. Min Act: -0.1700
Data Index: 8618429 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0369. Min Act: -0.1700
Data Index: 5238222 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0057. Min Act: -0.1700
Data Index: 2026622 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3807. Min Range: -5.3807
Max Act: 5.0057. Min Act: -0.1700
Data Index: 5718646 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9432. Min Act: -0.1700
Data Index: 8347997 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9744. Min Act: -0.1700
Data Index: 1756133 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9744. Min Act: -0.1700
Data Index: 6310315 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9432. Min Act: -0.1700
Data Index: 3979625 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9432. Min Act: -0.1700
Data Index: 249132 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9432. Min Act: -0.1700
Data Index: 1126371 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.8807. Min Act: -0.1700
Data Index: 17796 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5186223 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9432. Min Act: -0.1700
Data Index: 6894620 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3807. Min Range: -5.3807
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5324057 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19