Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3241. Min Range: -10.3241
Max Act: 10.3241. Min Act: -0.1700
Data Index: 1418794 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.8241. Min Act: -0.1700
Data Index: 1418793 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.7616. Min Act: -0.1700
Data Index: 3877217 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.4491. Min Act: -0.1700
Data Index: 1426063 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.3241. Min Act: -0.1700
Data Index: 2200364 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.2616. Min Act: -0.1700
Data Index: 2244143 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.0741. Min Act: -0.1700
Data Index: 193745 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3241. Min Range: -10.3241
Max Act: 9.0116. Min Act: -0.1700
Data Index: 5170233 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.9491. Min Act: -0.1700
Data Index: 392263 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.9491. Min Act: -0.1700
Data Index: 7861428 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8241. Min Act: -0.1700
Data Index: 6127733 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8866. Min Act: -0.1700
Data Index: 7003057 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8866. Min Act: -0.1700
Data Index: 6495478 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8866. Min Act: -0.1700
Data Index: 1450405 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.7616. Min Act: -0.1700
Data Index: 6069840 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8241. Min Act: -0.1700
Data Index: 6492838 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.7616. Min Act: -0.1700
Data Index: 4009148 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.8866. Min Act: -0.1700
Data Index: 2281787 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.6991. Min Act: -0.1700
Data Index: 5773574 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3241. Min Range: -10.3241
Max Act: 8.6991. Min Act: -0.1700
Data Index: 2965854 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19