Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3923 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0312. Min Range: -9.0312
Max Act: 9.0312. Min Act: -0.1700
Data Index: 7368655 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.8437. Min Act: -0.1700
Data Index: 314667 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.7812. Min Act: -0.1700
Data Index: 4067504 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.5937. Min Act: -0.1700
Data Index: 744628 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.5312. Min Act: -0.1700
Data Index: 440005 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.5312. Min Act: -0.1700
Data Index: 6982282 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.5312. Min Act: -0.1700
Data Index: 7960197 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4687. Min Act: -0.1700
Data Index: 2322943 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4687. Min Act: -0.1700
Data Index: 3037229 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4687. Min Act: -0.1700
Data Index: 6290033 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4687. Min Act: -0.1700
Data Index: 2777131 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4687. Min Act: -0.1700
Data Index: 4961891 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4062. Min Act: -0.1700
Data Index: 6303087 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.4062. Min Act: -0.1700
Data Index: 8705237 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.3437. Min Act: -0.1700
Data Index: 7403332 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.3437. Min Act: -0.1700
Data Index: 7917075 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.3437. Min Act: -0.1700
Data Index: 7047343 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.3437. Min Act: -0.1700
Data Index: 58423 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.3437. Min Act: -0.1700
Data Index: 6171106 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0312. Min Range: -9.0312
Max Act: 8.2812. Min Act: -0.1700
Data Index: 2817615 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19