Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0860. Min Range: -6.0860
Max Act: 6.0860. Min Act: -0.1700
Data Index: 3630435 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7735. Min Act: -0.1700
Data Index: 4779538 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7735. Min Act: -0.1700
Data Index: 5422087 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4779537 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7110. Min Act: -0.1700
Data Index: 2597079 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6798. Min Act: -0.1700
Data Index: 1986844 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6798. Min Act: -0.1700
Data Index: 6347524 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1855600 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5860. Min Act: -0.1700
Data Index: 318542 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5860. Min Act: -0.1700
Data Index: 5234218 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5860. Min Act: -0.1700
Data Index: 5591525 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2089200 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5548. Min Act: -0.1700
Data Index: 542294 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.4610. Min Act: -0.1700
Data Index: 1559118 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.4298. Min Act: -0.1700
Data Index: 913601 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.4298. Min Act: -0.1700
Data Index: 8164834 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.3985. Min Act: -0.1700
Data Index: 1434155 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.3985. Min Act: -0.1700
Data Index: 2590052 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.3985. Min Act: -0.1700
Data Index: 53220 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.3985. Min Act: -0.1700
Data Index: 3188333 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19