Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7893663 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.8428. Min Act: -0.1700
Data Index: 6353633 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7803. Min Act: -0.1700
Data Index: 456175 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7803. Min Act: -0.1700
Data Index: 5341803 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7490. Min Act: -0.1700
Data Index: 7947633 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7490. Min Act: -0.1700
Data Index: 3426098 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7178. Min Act: -0.1700
Data Index: 5931703 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7178. Min Act: -0.1700
Data Index: 4163918 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7178. Min Act: -0.1700
Data Index: 907813 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.7178. Min Act: -0.1700
Data Index: 4073896 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6865. Min Act: -0.1700
Data Index: 7289581 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6553. Min Act: -0.1700
Data Index: 7458809 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6865. Min Act: -0.1700
Data Index: 3408950 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6865. Min Act: -0.1700
Data Index: 6544282 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6865. Min Act: -0.1700
Data Index: 8757355 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6553. Min Act: -0.1700
Data Index: 816997 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6240. Min Act: -0.1700
Data Index: 3463595 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6553. Min Act: -0.1700
Data Index: 4600149 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6865. Min Act: -0.1700
Data Index: 4462448 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9053. Min Range: -4.9053
Max Act: 4.6553. Min Act: -0.1700
Data Index: 554720 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19