Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4202 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1145. Min Range: -7.1145
Max Act: 7.1145. Min Act: -0.1700
Data Index: 2249584 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.8645. Min Act: -0.1700
Data Index: 1106380 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.8020. Min Act: -0.1700
Data Index: 2668832 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.7083. Min Act: -0.1700
Data Index: 8270533 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6770. Min Act: -0.1700
Data Index: 7759506 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6770. Min Act: -0.1700
Data Index: 3382700 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6770. Min Act: -0.1700
Data Index: 6164723 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6770. Min Act: -0.1700
Data Index: 8561810 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6145. Min Act: -0.1700
Data Index: 6424399 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6145. Min Act: -0.1700
Data Index: 5210066 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.6145. Min Act: -0.1700
Data Index: 6116981 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5833. Min Act: -0.1700
Data Index: 2320003 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5833. Min Act: -0.1700
Data Index: 4149278 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5520. Min Act: -0.1700
Data Index: 4876587 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5520. Min Act: -0.1700
Data Index: 197708 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5208. Min Act: -0.1700
Data Index: 7049446 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.5208. Min Act: -0.1700
Data Index: 6512325 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.4895. Min Act: -0.1700
Data Index: 4227494 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.4895. Min Act: -0.1700
Data Index: 5087822 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1145. Min Range: -7.1145
Max Act: 6.4895. Min Act: -0.1700
Data Index: 1008141 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19