Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 943 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.6017. Min Act: -0.1700
Data Index: 4243151 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.5078. Min Act: -0.1700
Data Index: 8435833 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.4608. Min Act: -0.1700
Data Index: 4588395 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3668. Min Act: -0.1700
Data Index: 101468 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3354. Min Act: -0.1700
Data Index: 4538667 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3354. Min Act: -0.1700
Data Index: 5026565 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3354. Min Act: -0.1700
Data Index: 221128 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 1065904 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3040. Min Act: -0.1700
Data Index: 2723102 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3354. Min Act: -0.1700
Data Index: 4453989 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3040. Min Act: -0.1700
Data Index: 2373283 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 3560231 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 5927879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 3010302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 2022365 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3040. Min Act: -0.1700
Data Index: 2239314 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 640125 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 4042432 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 2488585 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6017. Min Range: -3.6017
Max Act: 3.3197. Min Act: -0.1700
Data Index: 3423139 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19