Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5008 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.5785. Min Act: -0.1700
Data Index: 602013 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.3598. Min Act: -0.1700
Data Index: 1014414 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2973. Min Act: -0.1700
Data Index: 5322322 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2660. Min Act: -0.1700
Data Index: 7001874 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2035. Min Act: -0.1700
Data Index: 4375345 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2348. Min Act: -0.1700
Data Index: 577437 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2035. Min Act: -0.1700
Data Index: 3066110 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2035. Min Act: -0.1700
Data Index: 492164 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.2035. Min Act: -0.1700
Data Index: 4268339 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1723. Min Act: -0.1700
Data Index: 5204075 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1723. Min Act: -0.1700
Data Index: 5498978 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1723. Min Act: -0.1700
Data Index: 3350198 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1410. Min Act: -0.1700
Data Index: 839196 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1098. Min Act: -0.1700
Data Index: 6349627 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.1098. Min Act: -0.1700
Data Index: 141103 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.0785. Min Act: -0.1700
Data Index: 8010617 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.0785. Min Act: -0.1700
Data Index: 924616 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.0473. Min Act: -0.1700
Data Index: 7941836 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5785. Min Range: -7.5785
Max Act: 7.0473. Min Act: -0.1700
Data Index: 5199230 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5785. Min Range: -7.5785
Max Act: 6.9848. Min Act: -0.1700
Data Index: 5015134 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19