Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.8111. Min Act: -0.1700
Data Index: 1834250 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7799. Min Act: -0.1700
Data Index: 1666952 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7486. Min Act: -0.1700
Data Index: 8079806 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7174. Min Act: -0.1700
Data Index: 320028 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.7174. Min Act: -0.1700
Data Index: 82766 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6861. Min Act: -0.1700
Data Index: 5350578 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6549. Min Act: -0.1700
Data Index: 778245 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6549. Min Act: -0.1700
Data Index: 6141868 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6549. Min Act: -0.1700
Data Index: 1812456 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7337309 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7206159 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 8585217 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 3758356 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 511555 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5924. Min Act: -0.1700
Data Index: 1966078 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 4754304 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 4754290 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5299. Min Act: -0.1700
Data Index: 4384004 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 8080817 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8111. Min Range: -5.8111
Max Act: 5.5611. Min Act: -0.1700
Data Index: 6088515 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19