Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3410. Min Range: -5.3410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 4347673 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3410. Min Range: -5.3410
Max Act: 5.1535. Min Act: -0.1700
Data Index: 7580569 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3410. Min Range: -5.3410
Max Act: 5.0285. Min Act: -0.1700
Data Index: 4221488 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9973. Min Act: -0.1700
Data Index: 3328020 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9973. Min Act: -0.1700
Data Index: 696990 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9973. Min Act: -0.1700
Data Index: 8447945 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9660. Min Act: -0.1700
Data Index: 1445194 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9348. Min Act: -0.1700
Data Index: 4711718 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9348. Min Act: -0.1700
Data Index: 2891918 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9348. Min Act: -0.1700
Data Index: 4295791 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 6884196 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9348. Min Act: -0.1700
Data Index: 732766 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.8723. Min Act: -0.1700
Data Index: 4595016 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 3865740 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 5068807 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 958865 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 4268392 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 5881636 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 265982 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3410. Min Range: -5.3410
Max Act: 4.9035. Min Act: -0.1700
Data Index: 2576457 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19