Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.7240. Min Act: -0.1700
Data Index: 5182227 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.6302. Min Act: -0.1700
Data Index: 6792520 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 8630418 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5365. Min Act: -0.1700
Data Index: 828546 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5365. Min Act: -0.1700
Data Index: 2442863 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5052. Min Act: -0.1700
Data Index: 8754468 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5052. Min Act: -0.1700
Data Index: 3539160 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.5052. Min Act: -0.1700
Data Index: 8531281 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.4740. Min Act: -0.1700
Data Index: 1568564 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.4427. Min Act: -0.1700
Data Index: 3177175 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.4115. Min Act: -0.1700
Data Index: 749717 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.4115. Min Act: -0.1700
Data Index: 1943992 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.4115. Min Act: -0.1700
Data Index: 7452177 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3802. Min Act: -0.1700
Data Index: 4709049 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3802. Min Act: -0.1700
Data Index: 7847979 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3490. Min Act: -0.1700
Data Index: 1960762 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3802. Min Act: -0.1700
Data Index: 7341200 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7414497 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7457044 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7240. Min Range: -5.7240
Max Act: 5.3490. Min Act: -0.1700
Data Index: 4807161 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19