Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4118 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.2722. Min Act: -0.1700
Data Index: 7925280 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.2097. Min Act: -0.1700
Data Index: 6316180 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.1785. Min Act: -0.1700
Data Index: 8816102 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.1472. Min Act: -0.1700
Data Index: 3015370 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.1160. Min Act: -0.1700
Data Index: 379371 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.1160. Min Act: -0.1700
Data Index: 5054123 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.1160. Min Act: -0.1700
Data Index: 2339497 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.0535. Min Act: -0.1700
Data Index: 34285 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.0535. Min Act: -0.1700
Data Index: 2391956 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.0222. Min Act: -0.1700
Data Index: 5637692 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2722. Min Range: -7.2722
Max Act: 7.0847. Min Act: -0.1700
Data Index: 8257014 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9910. Min Act: -0.1700
Data Index: 1071170 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9597. Min Act: -0.1700
Data Index: 501917 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9597. Min Act: -0.1700
Data Index: 6305175 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9597. Min Act: -0.1700
Data Index: 1840020 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9285. Min Act: -0.1700
Data Index: 8606987 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9285. Min Act: -0.1700
Data Index: 195080 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9597. Min Act: -0.1700
Data Index: 1252432 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9285. Min Act: -0.1700
Data Index: 4201332 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2722. Min Range: -7.2722
Max Act: 6.9285. Min Act: -0.1700
Data Index: 2272623 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19