Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4141 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 4985016 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 732797 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.4818. Min Act: -0.1700
Data Index: 4985011 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.4193. Min Act: -0.1700
Data Index: 2693753 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3568. Min Act: -0.1700
Data Index: 4985020 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 4985010 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 3176449 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4985004 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4985014 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 5529138 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3013610 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 679759 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5873490 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 3762803 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1693. Min Act: -0.1700
Data Index: 4985017 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1068. Min Act: -0.1700
Data Index: 4985019 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 5765671 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 820823 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 5910168 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1983837 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19