Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.5869. Min Act: -0.1700
Data Index: 6129788 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.3994. Min Act: -0.1700
Data Index: 1763290 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.3682. Min Act: -0.1700
Data Index: 4050385 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.3057. Min Act: -0.1700
Data Index: 2320741 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.3057. Min Act: -0.1700
Data Index: 4931641 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.2744. Min Act: -0.1700
Data Index: 7000609 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.1494. Min Act: -0.1700
Data Index: 2312453 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5869. Min Range: -4.5869
Max Act: 4.0556. Min Act: -0.1700
Data Index: 37027 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9931. Min Act: -0.1700
Data Index: 1658366 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9931. Min Act: -0.1700
Data Index: 4626233 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9931. Min Act: -0.1700
Data Index: 2338158 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9619. Min Act: -0.1700
Data Index: 3316073 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 2998967 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 5152731 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.8993. Min Act: -0.1700
Data Index: 631603 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 5603859 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 3655024 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 2423102 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.9306. Min Act: -0.1700
Data Index: 6975165 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5869. Min Range: -4.5869
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1764574 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19