Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1674. Min Range: -9.1674
Max Act: 9.1674. Min Act: -0.1700
Data Index: 8312710 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.9799. Min Act: -0.1700
Data Index: 8359692 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.7924. Min Act: -0.1700
Data Index: 1108220 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.7924. Min Act: -0.1700
Data Index: 8127244 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.7299. Min Act: -0.1700
Data Index: 400912 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.6674. Min Act: -0.1700
Data Index: 910507 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.5424. Min Act: -0.1700
Data Index: 6787476 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4799. Min Act: -0.1700
Data Index: 4076643 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.5424. Min Act: -0.1700
Data Index: 6566134 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4799. Min Act: -0.1700
Data Index: 4882261 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 1412925 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 2713739 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 8049878 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 292087 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 3447104 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.4174. Min Act: -0.1700
Data Index: 3111039 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.3549. Min Act: -0.1700
Data Index: 3649623 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.3549. Min Act: -0.1700
Data Index: 8178422 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.3549. Min Act: -0.1700
Data Index: 3043495 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1674. Min Range: -9.1674
Max Act: 8.3549. Min Act: -0.1700
Data Index: 6032694 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19