Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.8835. Min Act: -0.1700
Data Index: 6689430 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6960. Min Act: -0.1700
Data Index: 229296 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6960. Min Act: -0.1700
Data Index: 490278 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6960. Min Act: -0.1700
Data Index: 790880 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6960. Min Act: -0.1700
Data Index: 1741430 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 7830716 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6335. Min Act: -0.1700
Data Index: 5300560 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 6934698 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 8354971 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 3822803 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 1429557 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 7155283 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6335. Min Act: -0.1700
Data Index: 1625850 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6335. Min Act: -0.1700
Data Index: 527037 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6335. Min Act: -0.1700
Data Index: 6407483 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6648. Min Act: -0.1700
Data Index: 6220467 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6335. Min Act: -0.1700
Data Index: 8002353 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6023. Min Act: -0.1700
Data Index: 2035322 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6023. Min Act: -0.1700
Data Index: 2865279 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8835. Min Range: -4.8835
Max Act: 4.6023. Min Act: -0.1700
Data Index: 722709 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19