Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.5739. Min Act: -0.1700
Data Index: 8642172 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.5114. Min Act: -0.1700
Data Index: 819566 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.4802. Min Act: -0.1700
Data Index: 3843407 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.4489. Min Act: -0.1700
Data Index: 6726705 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.4177. Min Act: -0.1700
Data Index: 519031 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3864. Min Act: -0.1700
Data Index: 7987383 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3864. Min Act: -0.1700
Data Index: 4949841 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.4177. Min Act: -0.1700
Data Index: 7912368 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3552. Min Act: -0.1700
Data Index: 7414623 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3552. Min Act: -0.1700
Data Index: 896349 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3239. Min Act: -0.1700
Data Index: 298822 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3552. Min Act: -0.1700
Data Index: 3587047 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3239. Min Act: -0.1700
Data Index: 6594049 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3239. Min Act: -0.1700
Data Index: 2566442 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.2927. Min Act: -0.1700
Data Index: 8372165 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3239. Min Act: -0.1700
Data Index: 8416146 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.3239. Min Act: -0.1700
Data Index: 8641492 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.2927. Min Act: -0.1700
Data Index: 4971872 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.2927. Min Act: -0.1700
Data Index: 6597818 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5739. Min Range: -5.5739
Max Act: 5.2927. Min Act: -0.1700
Data Index: 2485905 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19