Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.8973. Min Act: -0.1700
Data Index: 8803233 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.7722. Min Act: -0.1700
Data Index: 3402074 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.7097. Min Act: -0.1700
Data Index: 660500 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6784. Min Act: -0.1700
Data Index: 8768815 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6784. Min Act: -0.1700
Data Index: 4563128 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6784. Min Act: -0.1700
Data Index: 2439059 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6471. Min Act: -0.1700
Data Index: 5510360 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6471. Min Act: -0.1700
Data Index: 8586911 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1725449 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 618018 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 2749200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1067082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 379286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 1669831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 3294371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 157068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 532529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 193668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 511121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8973. Min Range: -3.8973
Max Act: 3.6158. Min Act: -0.1700
Data Index: 3355494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19