Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0954. Min Range: -6.0954
Max Act: 6.0954. Min Act: -0.1700
Data Index: 3988243 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.9392. Min Act: -0.1700
Data Index: 6714861 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.9392. Min Act: -0.1700
Data Index: 8714679 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8767. Min Act: -0.1700
Data Index: 2320749 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.9079. Min Act: -0.1700
Data Index: 1977777 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8767. Min Act: -0.1700
Data Index: 249148 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8767. Min Act: -0.1700
Data Index: 21157 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8454. Min Act: -0.1700
Data Index: 2769229 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8454. Min Act: -0.1700
Data Index: 6957327 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8142. Min Act: -0.1700
Data Index: 681005 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8142. Min Act: -0.1700
Data Index: 5519034 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.8142. Min Act: -0.1700
Data Index: 958204 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7517. Min Act: -0.1700
Data Index: 854214 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7829. Min Act: -0.1700
Data Index: 4959350 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7517. Min Act: -0.1700
Data Index: 6013807 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7517. Min Act: -0.1700
Data Index: 8178596 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7204. Min Act: -0.1700
Data Index: 8092991 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4811855 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4811852 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0954. Min Range: -6.0954
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6501857 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19