Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.6410. Min Act: -0.1700
Data Index: 7599589 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.5785. Min Act: -0.1700
Data Index: 1179005 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.5472. Min Act: -0.1700
Data Index: 22910 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.2347. Min Act: -0.1700
Data Index: 1232669 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.2035. Min Act: -0.1700
Data Index: 5915697 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.2035. Min Act: -0.1700
Data Index: 4981648 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.2035. Min Act: -0.1700
Data Index: 7026762 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.2035. Min Act: -0.1700
Data Index: 3001059 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.1722. Min Act: -0.1700
Data Index: 7345362 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.1410. Min Act: -0.1700
Data Index: 3850707 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.1097. Min Act: -0.1700
Data Index: 8324023 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.1097. Min Act: -0.1700
Data Index: 8401599 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.1097. Min Act: -0.1700
Data Index: 2915564 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 6707831 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 3568024 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 6295513 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 762675 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0785. Min Act: -0.1700
Data Index: 8593970 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0472. Min Act: -0.1700
Data Index: 1407122 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6410. Min Range: -5.6410
Max Act: 5.0472. Min Act: -0.1700
Data Index: 2796469 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19