Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5748 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.7571. Min Act: -0.1700
Data Index: 3250008 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.7259. Min Act: -0.1700
Data Index: 5971928 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.6009. Min Act: -0.1700
Data Index: 4596286 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5696. Min Act: -0.1700
Data Index: 756520 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5696. Min Act: -0.1700
Data Index: 2892305 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5696. Min Act: -0.1700
Data Index: 509305 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5696. Min Act: -0.1700
Data Index: 1588408 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5071. Min Act: -0.1700
Data Index: 1877541 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5071. Min Act: -0.1700
Data Index: 2958690 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.5071. Min Act: -0.1700
Data Index: 5985360 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4759. Min Act: -0.1700
Data Index: 7055102 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4446. Min Act: -0.1700
Data Index: 8714971 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4446. Min Act: -0.1700
Data Index: 2319208 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 7731654 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 6700056 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 6366552 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 2321913 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 5041710 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4134. Min Act: -0.1700
Data Index: 2418244 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7571. Min Range: -6.7571
Max Act: 6.4446. Min Act: -0.1700
Data Index: 1524850 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19