Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.8744. Min Act: -0.1700
Data Index: 6291385 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.7182. Min Act: -0.1700
Data Index: 2143304 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.7182. Min Act: -0.1700
Data Index: 4787494 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.6869. Min Act: -0.1700
Data Index: 6878397 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.4057. Min Act: -0.1700
Data Index: 4262258 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.4057. Min Act: -0.1700
Data Index: 6816419 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.4057. Min Act: -0.1700
Data Index: 8365069 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3744. Min Act: -0.1700
Data Index: 1662464 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3432. Min Act: -0.1700
Data Index: 6154 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3432. Min Act: -0.1700
Data Index: 5777129 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7329902 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3119. Min Act: -0.1700
Data Index: 5067520 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3119. Min Act: -0.1700
Data Index: 861328 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3119. Min Act: -0.1700
Data Index: 7063759 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2529319 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3432. Min Act: -0.1700
Data Index: 2077880 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3119. Min Act: -0.1700
Data Index: 5229757 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.3119. Min Act: -0.1700
Data Index: 5701483 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.2807. Min Act: -0.1700
Data Index: 4623511 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8744. Min Range: -5.8744
Max Act: 5.2182. Min Act: -0.1700
Data Index: 3091276 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19