Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.7759. Min Act: -0.1700
Data Index: 5087814 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.5884. Min Act: -0.1700
Data Index: 3951424 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.4322. Min Act: -0.1700
Data Index: 2889862 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.4009. Min Act: -0.1700
Data Index: 6838145 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.4009. Min Act: -0.1700
Data Index: 5894649 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.3697. Min Act: -0.1700
Data Index: 7047428 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.3072. Min Act: -0.1700
Data Index: 194786 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.3072. Min Act: -0.1700
Data Index: 7048018 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.2447. Min Act: -0.1700
Data Index: 2898369 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.2447. Min Act: -0.1700
Data Index: 1296352 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.2134. Min Act: -0.1700
Data Index: 2047528 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.2134. Min Act: -0.1700
Data Index: 8507563 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1822. Min Act: -0.1700
Data Index: 2000122 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1822. Min Act: -0.1700
Data Index: 7433044 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.2134. Min Act: -0.1700
Data Index: 4752841 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1822. Min Act: -0.1700
Data Index: 7213889 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1822. Min Act: -0.1700
Data Index: 1202457 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1509. Min Act: -0.1700
Data Index: 3511250 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1509. Min Act: -0.1700
Data Index: 4623986 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7759. Min Range: -6.7759
Max Act: 6.1509. Min Act: -0.1700
Data Index: 4684094 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19