Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5410. Min Range: -8.5410
Max Act: 8.5410. Min Act: -0.1700
Data Index: 2111519 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5410. Min Range: -8.5410
Max Act: 8.1035. Min Act: -0.1700
Data Index: 7644607 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 3989322 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.8222. Min Act: -0.1700
Data Index: 6516638 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.7910. Min Act: -0.1700
Data Index: 3287724 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.7910. Min Act: -0.1700
Data Index: 32341 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.7597. Min Act: -0.1699
Data Index: 4882805 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.6660. Min Act: -0.1700
Data Index: 6123595 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5722. Min Act: -0.1700
Data Index: 8822812 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 625966 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5097. Min Act: -0.1700
Data Index: 3838706 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 6539944 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 2552918 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5722. Min Act: -0.1700
Data Index: 6754865 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5097. Min Act: -0.1700
Data Index: 104387 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 5990110 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.5097. Min Act: -0.1700
Data Index: 3593662 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.4785. Min Act: -0.1700
Data Index: 4252680 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.4785. Min Act: -0.1700
Data Index: 8048990 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5410. Min Range: -8.5410
Max Act: 7.4160. Min Act: -0.1700
Data Index: 7802540 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19