Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.8050. Min Act: -0.1700
Data Index: 6612195 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3993861 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.7113. Min Act: -0.1700
Data Index: 3234786 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6488. Min Act: -0.1700
Data Index: 4768716 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6175. Min Act: -0.1700
Data Index: 7114035 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6175. Min Act: -0.1700
Data Index: 1568221 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6175. Min Act: -0.1700
Data Index: 4641683 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6175. Min Act: -0.1700
Data Index: 4429891 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.6175. Min Act: -0.1700
Data Index: 2898938 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5863. Min Act: -0.1700
Data Index: 939426 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5863. Min Act: -0.1700
Data Index: 1042966 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5550. Min Act: -0.1700
Data Index: 1037524 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2757990 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5550. Min Act: -0.1700
Data Index: 5378236 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.5238. Min Act: -0.1700
Data Index: 3829638 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.4613. Min Act: -0.1700
Data Index: 160521 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.4925. Min Act: -0.1700
Data Index: 4252410 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.4925. Min Act: -0.1700
Data Index: 983722 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.4925. Min Act: -0.1700
Data Index: 4884034 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8050. Min Range: -5.8050
Max Act: 5.4925. Min Act: -0.1700
Data Index: 1173129 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19