Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.5016. Min Act: -0.1700
Data Index: 484619 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3766. Min Act: -0.1700
Data Index: 743908 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3766. Min Act: -0.1700
Data Index: 1844828 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3454. Min Act: -0.1700
Data Index: 2758230 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3454. Min Act: -0.1700
Data Index: 8442908 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4740589 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.3454. Min Act: -0.1700
Data Index: 6146126 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2829. Min Act: -0.1700
Data Index: 5504933 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2829. Min Act: -0.1700
Data Index: 4103156 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2516. Min Act: -0.1700
Data Index: 8612877 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2516. Min Act: -0.1700
Data Index: 47747 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2516. Min Act: -0.1700
Data Index: 3104930 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.2204. Min Act: -0.1700
Data Index: 1365331 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1891. Min Act: -0.1700
Data Index: 1575328 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1266. Min Act: -0.1700
Data Index: 535142 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1579. Min Act: -0.1700
Data Index: 4386401 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1579. Min Act: -0.1700
Data Index: 4216736 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1579. Min Act: -0.1700
Data Index: 5748253 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1579. Min Act: -0.1700
Data Index: 1069170 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5016. Min Range: -6.5016
Max Act: 6.1579. Min Act: -0.1700
Data Index: 2194260 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19