Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 3906853 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.2160. Min Act: -0.1700
Data Index: 1899869 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3410. Min Range: -7.3410
Max Act: 7.0285. Min Act: -0.1700
Data Index: 3972215 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 2818180 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 8287002 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9973. Min Act: -0.1700
Data Index: 115536 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9660. Min Act: -0.1700
Data Index: 5273167 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9348. Min Act: -0.1700
Data Index: 2098682 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9348. Min Act: -0.1700
Data Index: 7979622 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8723. Min Act: -0.1700
Data Index: 1073793 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8723. Min Act: -0.1700
Data Index: 2617484 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8723. Min Act: -0.1700
Data Index: 2617644 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.9035. Min Act: -0.1700
Data Index: 3021832 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8410. Min Act: -0.1700
Data Index: 8665668 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8410. Min Act: -0.1700
Data Index: 7346292 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8098. Min Act: -0.1700
Data Index: 8632087 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8098. Min Act: -0.1700
Data Index: 7477384 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.8098. Min Act: -0.1700
Data Index: 6307223 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.7785. Min Act: -0.1700
Data Index: 161154 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3410. Min Range: -7.3410
Max Act: 6.7785. Min Act: -0.1700
Data Index: 6702254 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19