Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5561 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.8794. Min Act: -0.1700
Data Index: 7571657 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.8169. Min Act: -0.1700
Data Index: 7007437 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.7856. Min Act: -0.1700
Data Index: 8119 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.7074. Min Act: -0.1700
Data Index: 3767165 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.7074. Min Act: -0.1700
Data Index: 7662128 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.6918. Min Act: -0.1700
Data Index: 1813653 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.6918. Min Act: -0.1700
Data Index: 8112335 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.6918. Min Act: -0.1700
Data Index: 308652 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.6605. Min Act: -0.1700
Data Index: 6859750 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.6292. Min Act: -0.1700
Data Index: 3473407 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5822. Min Act: -0.1700
Data Index: 378309 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5822. Min Act: -0.1700
Data Index: 7518031 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5666. Min Act: -0.1700
Data Index: 3748631 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5666. Min Act: -0.1700
Data Index: 6367373 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5666. Min Act: -0.1700
Data Index: 197852 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5353. Min Act: -0.1700
Data Index: 6225539 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5196. Min Act: -0.1700
Data Index: 2908691 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5196. Min Act: -0.1700
Data Index: 1750645 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5196. Min Act: -0.1700
Data Index: 7662127 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8794. Min Range: -3.8794
Max Act: 3.5196. Min Act: -0.1700
Data Index: 179506 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19