Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3182. Min Range: -7.3182
Max Act: 7.3182. Min Act: -0.1700
Data Index: 20544 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.7557. Min Act: -0.1700
Data Index: 672633 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.7245. Min Act: -0.1700
Data Index: 1281041 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6932. Min Act: -0.1700
Data Index: 6525131 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 2782810 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 5810102 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 1166186 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 280294 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 8542159 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4756571 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 7125647 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 393920 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 6496189 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 6173667 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 850173 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5682. Min Act: -0.1700
Data Index: 1682894 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3030049 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5370. Min Act: -0.1700
Data Index: 2740366 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5370. Min Act: -0.1700
Data Index: 8753222 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3182. Min Range: -7.3182
Max Act: 6.5370. Min Act: -0.1700
Data Index: 988592 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19