Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5844. Min Range: -6.5844
Max Act: 6.5844. Min Act: -0.1700
Data Index: 1794215 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5844. Min Range: -6.5844
Max Act: 6.0844. Min Act: -0.1700
Data Index: 5474632 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5844. Min Range: -6.5844
Max Act: 6.0219. Min Act: -0.1700
Data Index: 7640161 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.9906. Min Act: -0.1700
Data Index: 611685 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.9281. Min Act: -0.1700
Data Index: 218917 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.8656. Min Act: -0.1700
Data Index: 3718899 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4421600 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.9281. Min Act: -0.1700
Data Index: 7708900 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5208758 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.8344. Min Act: -0.1700
Data Index: 6376019 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.8031. Min Act: -0.1700
Data Index: 4442096 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5113809 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5283404 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6362828 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7406. Min Act: -0.1700
Data Index: 2224952 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1154316 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.6781. Min Act: -0.1700
Data Index: 2339618 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.7094. Min Act: -0.1700
Data Index: 7240175 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.6781. Min Act: -0.1700
Data Index: 5340854 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5844. Min Range: -6.5844
Max Act: 5.6781. Min Act: -0.1700
Data Index: 3108075 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19