Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0410. Min Act: -0.1700
Data Index: 5962892 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0410. Min Act: -0.1700
Data Index: 1968705 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0410. Min Range: -7.0410
Max Act: 7.0097. Min Act: -0.1700
Data Index: 4426364 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.9160. Min Act: -0.1700
Data Index: 5962896 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.7285. Min Act: -0.1700
Data Index: 3344075 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6660. Min Act: -0.1700
Data Index: 3570376 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6660. Min Act: -0.1700
Data Index: 934555 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6660. Min Act: -0.1700
Data Index: 2647164 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6347. Min Act: -0.1700
Data Index: 3693087 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.6660. Min Act: -0.1700
Data Index: 6554633 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.5410. Min Act: -0.1700
Data Index: 346795 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4785. Min Act: -0.1700
Data Index: 8225044 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.5097. Min Act: -0.1700
Data Index: 2163552 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.5097. Min Act: -0.1700
Data Index: 862427 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4785. Min Act: -0.1700
Data Index: 1736482 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4472. Min Act: -0.1700
Data Index: 932260 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4472. Min Act: -0.1700
Data Index: 4338255 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4472. Min Act: -0.1700
Data Index: 8668040 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4160. Min Act: -0.1700
Data Index: 8668053 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0410. Min Range: -7.0410
Max Act: 6.4160. Min Act: -0.1700
Data Index: 4979188 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19