Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2372 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2855. Min Range: -6.2855
Max Act: 6.2855. Min Act: -0.1700
Data Index: 2969019 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.9417. Min Act: -0.1700
Data Index: 1613988 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.8480. Min Act: -0.1700
Data Index: 3599085 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.7855. Min Act: -0.1700
Data Index: 2179024 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.7542. Min Act: -0.1700
Data Index: 5965004 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1676613 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6605. Min Act: -0.1700
Data Index: 332169 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6605. Min Act: -0.1700
Data Index: 7299902 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5980. Min Act: -0.1700
Data Index: 2838819 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6292. Min Act: -0.1700
Data Index: 5996551 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6292. Min Act: -0.1700
Data Index: 8670514 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.6292. Min Act: -0.1700
Data Index: 4417744 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5980. Min Act: -0.1700
Data Index: 1544685 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5980. Min Act: -0.1700
Data Index: 7505731 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5667. Min Act: -0.1700
Data Index: 3074872 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5667. Min Act: -0.1700
Data Index: 878206 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5667. Min Act: -0.1700
Data Index: 8522759 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5355. Min Act: -0.1700
Data Index: 6271413 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.5355. Min Act: -0.1700
Data Index: 4004502 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2855. Min Range: -6.2855
Max Act: 5.4730. Min Act: -0.1700
Data Index: 6573064 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19