Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.6585. Min Act: -0.1700
Data Index: 7188410 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.5960. Min Act: -0.1700
Data Index: 5419562 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.2210. Min Act: -0.1700
Data Index: 2549566 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.2210. Min Act: -0.1700
Data Index: 2058814 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.1585. Min Act: -0.1700
Data Index: 346514 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0960. Min Act: -0.1700
Data Index: 4889390 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0960. Min Act: -0.1700
Data Index: 2835350 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0960. Min Act: -0.1700
Data Index: 6430605 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0960. Min Act: -0.1700
Data Index: 7732338 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 401944 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0960. Min Act: -0.1700
Data Index: 2288083 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 4159926 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 5656396 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6585. Min Range: -8.6585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 8621513 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 797136 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6585. Min Range: -8.6585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 1345116 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6585. Min Range: -8.6585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 776832 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6585. Min Range: -8.6585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 6913712 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6585. Min Range: -8.6585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 5312297 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6585. Min Range: -8.6585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 6646041 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19