Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.6114. Min Act: -0.1700
Data Index: 8553796 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.5176. Min Act: -0.1700
Data Index: 2411873 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.4551. Min Act: -0.1700
Data Index: 4351246 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.3614. Min Act: -0.1700
Data Index: 4438076 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.3301. Min Act: -0.1700
Data Index: 8225784 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.2989. Min Act: -0.1700
Data Index: 4707132 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.2676. Min Act: -0.1700
Data Index: 243910 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.2676. Min Act: -0.1700
Data Index: 4481956 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.2051. Min Act: -0.1700
Data Index: 7806513 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.1739. Min Act: -0.1700
Data Index: 7383259 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.1114. Min Act: -0.1700
Data Index: 1848287 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.1114. Min Act: -0.1700
Data Index: 3390768 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.0801. Min Act: -0.1700
Data Index: 683102 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.1114. Min Act: -0.1700
Data Index: 768559 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.0489. Min Act: -0.1700
Data Index: 2865116 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.0489. Min Act: -0.1700
Data Index: 6532364 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.0801. Min Act: -0.1700
Data Index: 4964130 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6114. Min Range: -6.6114
Max Act: 6.0176. Min Act: -0.1700
Data Index: 1890725 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6114. Min Range: -6.6114
Max Act: 5.9864. Min Act: -0.1700
Data Index: 6693231 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6114. Min Range: -6.6114
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1698802 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19