Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.7046. Min Act: -0.1700
Data Index: 2133536 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.5484. Min Act: -0.1700
Data Index: 6023145 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.1734. Min Act: -0.1700
Data Index: 4034003 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.1109. Min Act: -0.1700
Data Index: 5515135 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.0484. Min Act: -0.1700
Data Index: 6018836 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.0796. Min Act: -0.1700
Data Index: 4589725 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.0484. Min Act: -0.1700
Data Index: 1517535 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7046. Min Range: -7.7046
Max Act: 7.0171. Min Act: -0.1700
Data Index: 1037316 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9859. Min Act: -0.1700
Data Index: 2604473 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4639576 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9859. Min Act: -0.1700
Data Index: 8445063 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9546. Min Act: -0.1700
Data Index: 3031167 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9546. Min Act: -0.1700
Data Index: 1911767 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9546. Min Act: -0.1700
Data Index: 5410183 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4087666 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9234. Min Act: -0.1700
Data Index: 1696416 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9546. Min Act: -0.1700
Data Index: 5177022 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.9234. Min Act: -0.1700
Data Index: 5652858 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.8921. Min Act: -0.1700
Data Index: 5249991 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7046. Min Range: -7.7046
Max Act: 6.8921. Min Act: -0.1700
Data Index: 3892600 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19