Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5907 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0940. Min Range: -5.0940
Max Act: 5.0940. Min Act: -0.1700
Data Index: 528446 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0940. Min Range: -5.0940
Max Act: 5.0628. Min Act: -0.1700
Data Index: 1489681 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.9690. Min Act: -0.1700
Data Index: 7988432 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.9690. Min Act: -0.1700
Data Index: 8152693 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.9065. Min Act: -0.1700
Data Index: 8273462 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8753. Min Act: -0.1700
Data Index: 2007208 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8753. Min Act: -0.1700
Data Index: 750074 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8753. Min Act: -0.1700
Data Index: 5908847 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8440. Min Act: -0.1700
Data Index: 7780898 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8440. Min Act: -0.1700
Data Index: 7429967 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.8128. Min Act: -0.1700
Data Index: 7054096 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7503. Min Act: -0.1700
Data Index: 4617333 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7190. Min Act: -0.1700
Data Index: 7821414 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7190. Min Act: -0.1700
Data Index: 7889034 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4670887 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7190. Min Act: -0.1700
Data Index: 3312199 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.7190. Min Act: -0.1700
Data Index: 6629979 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.6878. Min Act: -0.1700
Data Index: 837296 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.6878. Min Act: -0.1700
Data Index: 1038674 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0940. Min Range: -5.0940
Max Act: 4.6878. Min Act: -0.1700
Data Index: 5256670 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19