Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5309 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.4447. Min Act: -0.1700
Data Index: 1701271 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.3822. Min Act: -0.1700
Data Index: 3370062 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.3197. Min Act: -0.1700
Data Index: 6453408 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.2259. Min Act: -0.1700
Data Index: 1489165 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.1009. Min Act: -0.1700
Data Index: 2806847 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.0384. Min Act: -0.1700
Data Index: 8312078 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.0072. Min Act: -0.1700
Data Index: 4508760 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9759. Min Act: -0.1700
Data Index: 3938796 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9759. Min Act: -0.1700
Data Index: 917015 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9759. Min Act: -0.1700
Data Index: 2899721 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4447. Min Range: -7.4447
Max Act: 7.0072. Min Act: -0.1700
Data Index: 4678992 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9447. Min Act: -0.1700
Data Index: 8290054 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9447. Min Act: -0.1700
Data Index: 341271 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9447. Min Act: -0.1700
Data Index: 7226467 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.9134. Min Act: -0.1700
Data Index: 3499115 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.8822. Min Act: -0.1700
Data Index: 6992853 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.8822. Min Act: -0.1700
Data Index: 6302890 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.8197. Min Act: -0.1700
Data Index: 5820620 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.8197. Min Act: -0.1700
Data Index: 200054 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4447. Min Range: -7.4447
Max Act: 6.8197. Min Act: -0.1700
Data Index: 5128145 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19