Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4496 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.3056. Min Act: -0.1700
Data Index: 2331146 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.2431. Min Act: -0.1700
Data Index: 8626819 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3389851 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.2119. Min Act: -0.1700
Data Index: 7970781 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.2119. Min Act: -0.1700
Data Index: 8171998 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.2431. Min Act: -0.1700
Data Index: 29934 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 7970775 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 4848407 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1806. Min Act: -0.1700
Data Index: 7704464 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1494. Min Act: -0.1700
Data Index: 4092297 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1494. Min Act: -0.1700
Data Index: 7970776 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1494. Min Act: -0.1700
Data Index: 7970786 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1494. Min Act: -0.1700
Data Index: 8140955 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1494. Min Act: -0.1700
Data Index: 7970779 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1181. Min Act: -0.1700
Data Index: 7613789 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0869. Min Act: -0.1700
Data Index: 7970770 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 7970784 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.1181. Min Act: -0.1700
Data Index: 889923 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 6781276 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3056. Min Range: -5.3056
Max Act: 5.0556. Min Act: -0.1700
Data Index: 4595173 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19