Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.7579. Min Act: -0.1700
Data Index: 1986003 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.7267. Min Act: -0.1700
Data Index: 4760121 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4766. Min Act: -0.1700
Data Index: 4060759 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4766. Min Act: -0.1700
Data Index: 159409 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4766. Min Act: -0.1700
Data Index: 2823218 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4454. Min Act: -0.1700
Data Index: 5992528 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4141. Min Act: -0.1700
Data Index: 7529854 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4454. Min Act: -0.1700
Data Index: 1803740 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5108447 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4141. Min Act: -0.1700
Data Index: 4562639 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5151908 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3516. Min Act: -0.1700
Data Index: 1923976 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3829. Min Act: -0.1700
Data Index: 4376936 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3516. Min Act: -0.1700
Data Index: 408301 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3516. Min Act: -0.1700
Data Index: 2372901 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3516. Min Act: -0.1700
Data Index: 3993896 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3204. Min Act: -0.1700
Data Index: 5512699 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3204. Min Act: -0.1700
Data Index: 7033469 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3204. Min Act: -0.1700
Data Index: 4559909 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7579. Min Range: -4.7579
Max Act: 4.3204. Min Act: -0.1700
Data Index: 1847892 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19