Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2323 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5127. Min Range: -6.5127
Max Act: 6.5127. Min Act: -0.1700
Data Index: 2523028 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5127. Min Range: -6.5127
Max Act: 6.1377. Min Act: -0.1700
Data Index: 2043940 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5127. Min Range: -6.5127
Max Act: 6.0752. Min Act: -0.1700
Data Index: 7024134 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5127. Min Range: -6.5127
Max Act: 6.0127. Min Act: -0.1700
Data Index: 5618631 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5912269 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.9190. Min Act: -0.1700
Data Index: 7760199 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 5661179 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 2338201 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8877. Min Act: -0.1700
Data Index: 6091061 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 7480612 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8252. Min Act: -0.1700
Data Index: 5225160 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 5996326 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 2503667 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 3758288 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 6982999 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4301572 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 5926335 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8565. Min Act: -0.1700
Data Index: 7571444 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8252. Min Act: -0.1700
Data Index: 96920 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5127. Min Range: -6.5127
Max Act: 5.8252. Min Act: -0.1700
Data Index: 7091407 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19