Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2342 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.9063. Min Act: -0.1698
Data Index: 6114574 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.8269. Min Act: -0.1700
Data Index: 5214507 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.7792. Min Act: -0.1700
Data Index: 7542796 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.7313. Min Act: -0.1700
Data Index: 1385714 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.7313. Min Act: -0.1700
Data Index: 5399157 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.7153. Min Act: -0.1700
Data Index: 5426656 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.7153. Min Act: -0.1700
Data Index: 7392011 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6993. Min Act: -0.1700
Data Index: 6851735 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6993. Min Act: -0.1700
Data Index: 5623861 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6833. Min Act: -0.1700
Data Index: 5474033 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6993. Min Act: -0.1700
Data Index: 1795758 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6673. Min Act: -0.1700
Data Index: 3027586 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6833. Min Act: -0.1700
Data Index: 3740607 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6673. Min Act: -0.1700
Data Index: 6114573 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6512. Min Act: -0.1699
Data Index: 8285740 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6512. Min Act: -0.1700
Data Index: 948500 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6352. Min Act: -0.1700
Data Index: 2126626 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6512. Min Act: -0.1700
Data Index: 3209349 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6352. Min Act: -0.1700
Data Index: 7453601 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9063. Min Range: -2.9063
Max Act: 2.6352. Min Act: -0.1700
Data Index: 7318865 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19