Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.6894. Min Act: -0.1700
Data Index: 3741408 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.6894. Min Act: -0.1700
Data Index: 4933169 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.6582. Min Act: -0.1700
Data Index: 6049084 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.6582. Min Act: -0.1700
Data Index: 5707375 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.5644. Min Act: -0.1700
Data Index: 2990230 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.4707. Min Act: -0.1700
Data Index: 8191546 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.4394. Min Act: -0.1700
Data Index: 7830907 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.3457. Min Act: -0.1700
Data Index: 5864829 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3378238 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.3457. Min Act: -0.1700
Data Index: 1054125 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3622758 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.3457. Min Act: -0.1700
Data Index: 2997259 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2832. Min Act: -0.1700
Data Index: 148181 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2832. Min Act: -0.1700
Data Index: 3306016 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2832. Min Act: -0.1700
Data Index: 8755058 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2519. Min Act: -0.1700
Data Index: 4357078 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2519. Min Act: -0.1700
Data Index: 1744220 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.1894. Min Act: -0.1700
Data Index: 7941994 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2519. Min Act: -0.1700
Data Index: 4963807 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6894. Min Range: -6.6894
Max Act: 6.2207. Min Act: -0.1700
Data Index: 5482182 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19