Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.2410. Min Act: -0.1700
Data Index: 7348428 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.1624. Min Act: -0.1700
Data Index: 6679431 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.0836. Min Act: -0.1700
Data Index: 4411726 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.0836. Min Act: -0.1700
Data Index: 2602710 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.0205. Min Act: -0.1700
Data Index: 6547589 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.0047. Min Act: -0.1700
Data Index: 2779660 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2410. Min Range: -3.2410
Max Act: 3.0047. Min Act: -0.1700
Data Index: 4990242 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9731. Min Act: -0.1700
Data Index: 6961809 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9731. Min Act: -0.1700
Data Index: 3231284 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9731. Min Act: -0.1700
Data Index: 7381941 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9414. Min Act: -0.1700
Data Index: 4312900 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9256. Min Act: -0.1700
Data Index: 2001637 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9097. Min Act: -0.1700
Data Index: 7093788 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9097. Min Act: -0.1700
Data Index: 5832431 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9097. Min Act: -0.1700
Data Index: 1149537 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.9097. Min Act: -0.1700
Data Index: 8555713 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.8780. Min Act: -0.1700
Data Index: 4909215 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.8780. Min Act: -0.1700
Data Index: 1848366 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.8939. Min Act: -0.1700
Data Index: 5303698 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2410. Min Range: -3.2410
Max Act: 2.8939. Min Act: -0.1700
Data Index: 2373881 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19