Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.6975. Min Act: -0.1700
Data Index: 223552 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.6975. Min Act: -0.1700
Data Index: 4950625 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.6350. Min Act: -0.1700
Data Index: 7759747 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.6193. Min Act: -0.1700
Data Index: 2707200 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.6193. Min Act: -0.1700
Data Index: 4622027 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5723. Min Act: -0.1700
Data Index: 2329456 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5097. Min Act: -0.1700
Data Index: 3864265 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5410. Min Act: -0.1700
Data Index: 2508336 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5254. Min Act: -0.1700
Data Index: 6297575 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5410. Min Act: -0.1700
Data Index: 6605346 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5097. Min Act: -0.1700
Data Index: 4726456 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5097. Min Act: -0.1700
Data Index: 8659254 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.5097. Min Act: -0.1700
Data Index: 5239015 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4941. Min Act: -0.1700
Data Index: 411460 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4784. Min Act: -0.1700
Data Index: 109642 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4627. Min Act: -0.1700
Data Index: 5416884 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4784. Min Act: -0.1700
Data Index: 411459 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4627. Min Act: -0.1700
Data Index: 2320094 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4627. Min Act: -0.1700
Data Index: 212530 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6975. Min Range: -3.6975
Max Act: 3.4314. Min Act: -0.1700
Data Index: 7389826 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19