Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1097. Min Range: -8.1097
Max Act: 8.1097. Min Act: -0.1700
Data Index: 4611124 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1097. Min Range: -8.1097
Max Act: 7.4534. Min Act: -0.1700
Data Index: 7134773 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1097. Min Range: -8.1097
Max Act: 7.1097. Min Act: -0.1700
Data Index: 7523112 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.9534. Min Act: -0.1700
Data Index: 1303534 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.9534. Min Act: -0.1700
Data Index: 3970744 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.9222. Min Act: -0.1700
Data Index: 5634799 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.9222. Min Act: -0.1700
Data Index: 7598473 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.8909. Min Act: -0.1700
Data Index: 1008310 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.8597. Min Act: -0.1700
Data Index: 4002867 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.8909. Min Act: -0.1700
Data Index: 7204980 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.8909. Min Act: -0.1700
Data Index: 7340093 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7972. Min Act: -0.1700
Data Index: 7719894 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.8284. Min Act: -0.1700
Data Index: 6266458 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7972. Min Act: -0.1700
Data Index: 4578176 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7972. Min Act: -0.1700
Data Index: 676522 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7972. Min Act: -0.1700
Data Index: 8054340 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7659. Min Act: -0.1700
Data Index: 3456395 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7659. Min Act: -0.1700
Data Index: 6470110 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7659. Min Act: -0.1700
Data Index: 6228458 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1097. Min Range: -8.1097
Max Act: 6.7347. Min Act: -0.1700
Data Index: 7067411 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19