Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4934 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.2847. Min Act: -0.1700
Data Index: 3669691 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.1597. Min Act: -0.1700
Data Index: 434753 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.1285. Min Act: -0.1700
Data Index: 4520960 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.0972. Min Act: -0.1700
Data Index: 5020946 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.0972. Min Act: -0.1700
Data Index: 4947891 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.0035. Min Act: -0.1700
Data Index: 8049171 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2847. Min Range: -6.2847
Max Act: 6.0035. Min Act: -0.1700
Data Index: 2224815 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.9097. Min Act: -0.1700
Data Index: 887659 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.9410. Min Act: -0.1700
Data Index: 5927475 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8472. Min Act: -0.1700
Data Index: 6803418 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8472. Min Act: -0.1700
Data Index: 855981 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8472. Min Act: -0.1700
Data Index: 4947488 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8785. Min Act: -0.1700
Data Index: 88025 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8472. Min Act: -0.1700
Data Index: 2596626 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8160. Min Act: -0.1700
Data Index: 6932013 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8160. Min Act: -0.1700
Data Index: 8608630 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8160. Min Act: -0.1700
Data Index: 8458256 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.8160. Min Act: -0.1700
Data Index: 8668765 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.7847. Min Act: -0.1700
Data Index: 664257 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2847. Min Range: -6.2847
Max Act: 5.7847. Min Act: -0.1700
Data Index: 6842535 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19