Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.6923. Min Act: -0.1700
Data Index: 3561451 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.5673. Min Act: -0.1700
Data Index: 6473825 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.5048. Min Act: -0.1700
Data Index: 7245016 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.5048. Min Act: -0.1700
Data Index: 1106329 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.4423. Min Act: -0.1700
Data Index: 7463476 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.4423. Min Act: -0.1700
Data Index: 4007347 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.3798. Min Act: -0.1700
Data Index: 3924864 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.3798. Min Act: -0.1700
Data Index: 7657179 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.3173. Min Act: -0.1700
Data Index: 4828004 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.3173. Min Act: -0.1700
Data Index: 3083961 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.3173. Min Act: -0.1700
Data Index: 2209121 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.2548. Min Act: -0.1700
Data Index: 6418998 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.2548. Min Act: -0.1700
Data Index: 5540353 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1923. Min Act: -0.1700
Data Index: 111910 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1923. Min Act: -0.1700
Data Index: 1530453 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1923. Min Act: -0.1700
Data Index: 40848 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.2548. Min Act: -0.1700
Data Index: 7445223 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1923. Min Act: -0.1700
Data Index: 3944044 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1298. Min Act: -0.1700
Data Index: 5703308 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6923. Min Range: -9.6923
Max Act: 9.1298. Min Act: -0.1700
Data Index: 3696616 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19