Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.7312. Min Act: -0.1700
Data Index: 4532175 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.5750. Min Act: -0.1700
Data Index: 875766 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.4812. Min Act: -0.1700
Data Index: 7557698 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.5437. Min Act: -0.1700
Data Index: 875765 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.4500. Min Act: -0.1700
Data Index: 1202708 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.4187. Min Act: -0.1700
Data Index: 383571 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.4187. Min Act: -0.1700
Data Index: 7302371 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.4187. Min Act: -0.1700
Data Index: 4081594 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 4695308 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 4181625 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 122733 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3250. Min Act: -0.1700
Data Index: 1488154 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3250. Min Act: -0.1700
Data Index: 1688350 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.3250. Min Act: -0.1700
Data Index: 7314869 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2625. Min Act: -0.1700
Data Index: 1688349 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2937. Min Act: -0.1700
Data Index: 3161531 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2625. Min Act: -0.1700
Data Index: 8599385 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2625. Min Act: -0.1700
Data Index: 4435219 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2312. Min Act: -0.1700
Data Index: 8564245 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7312. Min Range: -5.7312
Max Act: 5.2312. Min Act: -0.1700
Data Index: 1239505 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19