Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 274 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.2939. Min Act: -0.1700
Data Index: 2612961 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.2002. Min Act: -0.1700
Data Index: 7767499 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.2002. Min Act: -0.1700
Data Index: 442425 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.1377. Min Act: -0.1700
Data Index: 8673212 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.1064. Min Act: -0.1700
Data Index: 7882678 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.0752. Min Act: -0.1700
Data Index: 5215756 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.0439. Min Act: -0.1700
Data Index: 252768 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.0127. Min Act: -0.1700
Data Index: 7623481 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2939. Min Range: -7.2939
Max Act: 7.0127. Min Act: -0.1700
Data Index: 1169819 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5110901 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5244439 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.9189. Min Act: -0.1700
Data Index: 2217435 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.9189. Min Act: -0.1700
Data Index: 5908553 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5698181 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8877. Min Act: -0.1700
Data Index: 5101739 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.9189. Min Act: -0.1700
Data Index: 3567044 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8564. Min Act: -0.1700
Data Index: 5283716 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8564. Min Act: -0.1700
Data Index: 4413881 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8564. Min Act: -0.1700
Data Index: 1749204 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2939. Min Range: -7.2939
Max Act: 6.8252. Min Act: -0.1700
Data Index: 5297823 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19