Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1489. Min Range: -4.1489
Max Act: 4.1489. Min Act: -0.1700
Data Index: 5590158 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1489. Min Range: -4.1489
Max Act: 4.0552. Min Act: -0.1700
Data Index: 4308310 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8676. Min Act: -0.1700
Data Index: 1663530 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7738. Min Act: -0.1700
Data Index: 1767287 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7112. Min Act: -0.1700
Data Index: 3199089 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7425. Min Act: -0.1700
Data Index: 7647092 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4571063 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7425. Min Act: -0.1700
Data Index: 6222227 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7112. Min Act: -0.1700
Data Index: 8436980 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7112. Min Act: -0.1700
Data Index: 7233502 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 6639803 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 8218928 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 1797463 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 1876980 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 3361062 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6486. Min Act: -0.1700
Data Index: 6561799 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6799. Min Act: -0.1700
Data Index: 5080634 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6486. Min Act: -0.1700
Data Index: 7454176 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6173. Min Act: -0.1700
Data Index: 4256978 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.6486. Min Act: -0.1700
Data Index: 7031894 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19