Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.7804. Min Act: -0.1700
Data Index: 8660562 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.6867. Min Act: -0.1700
Data Index: 7310801 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.6867. Min Act: -0.1700
Data Index: 8277450 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.6867. Min Act: -0.1700
Data Index: 62836 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5617. Min Act: -0.1700
Data Index: 420088 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5617. Min Act: -0.1700
Data Index: 3191733 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5304. Min Act: -0.1700
Data Index: 1210536 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5304. Min Act: -0.1700
Data Index: 3657006 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5304. Min Act: -0.1700
Data Index: 233519 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5304. Min Act: -0.1700
Data Index: 5725172 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.5304. Min Act: -0.1700
Data Index: 6786045 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4992. Min Act: -0.1700
Data Index: 5189678 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4992. Min Act: -0.1700
Data Index: 4535320 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4679. Min Act: -0.1700
Data Index: 2484336 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4367. Min Act: -0.1700
Data Index: 6729933 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4367. Min Act: -0.1700
Data Index: 4029682 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.4054. Min Act: -0.1700
Data Index: 3133117 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.3429. Min Act: -0.1700
Data Index: 736720 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.3429. Min Act: -0.1700
Data Index: 3329461 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7804. Min Range: -6.7804
Max Act: 6.3429. Min Act: -0.1700
Data Index: 3600267 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19