Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2313. Min Range: -6.2313
Max Act: 6.2313. Min Act: -0.1700
Data Index: 7724722 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2313. Min Range: -6.2313
Max Act: 6.1063. Min Act: -0.1700
Data Index: 5054653 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2313. Min Range: -6.2313
Max Act: 6.0126. Min Act: -0.1700
Data Index: 6945915 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.9188. Min Act: -0.1700
Data Index: 8769924 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.9188. Min Act: -0.1700
Data Index: 7876017 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.9188. Min Act: -0.1700
Data Index: 705100 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.8563. Min Act: -0.1700
Data Index: 7294415 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5930728 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.8563. Min Act: -0.1700
Data Index: 7679098 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.8563. Min Act: -0.1700
Data Index: 2124962 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7938. Min Act: -0.1700
Data Index: 6315219 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7938. Min Act: -0.1700
Data Index: 3291814 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 7650472 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 4482836 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 509201 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 3166967 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7001. Min Act: -0.1700
Data Index: 6370535 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 1660174 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7001. Min Act: -0.1700
Data Index: 6414972 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.6688. Min Act: -0.1700
Data Index: 3806830 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19