Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.2410. Min Act: -0.1700
Data Index: 2760964 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.2097. Min Act: -0.1700
Data Index: 8776592 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2410. Min Range: -6.2410
Max Act: 6.0222. Min Act: -0.1700
Data Index: 5795729 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1662987 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.9285. Min Act: -0.1700
Data Index: 8821174 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.8347. Min Act: -0.1700
Data Index: 2254477 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.8035. Min Act: -0.1700
Data Index: 1402957 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.8347. Min Act: -0.1700
Data Index: 8422199 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3697280 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 8791425 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 7200901 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 2776808 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7410. Min Act: -0.1700
Data Index: 4042094 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7097. Min Act: -0.1700
Data Index: 8671738 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7097. Min Act: -0.1700
Data Index: 7798799 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7097. Min Act: -0.1700
Data Index: 6778878 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.7097. Min Act: -0.1700
Data Index: 5638914 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.6785. Min Act: -0.1700
Data Index: 1687390 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.6785. Min Act: -0.1700
Data Index: 2760968 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2410. Min Range: -6.2410
Max Act: 5.6785. Min Act: -0.1700
Data Index: 7921029 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19