Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.4890. Min Act: -0.1700
Data Index: 2807577 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.4265. Min Act: -0.1700
Data Index: 8214397 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3953. Min Act: -0.1700
Data Index: 1670820 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3953. Min Act: -0.1700
Data Index: 7006859 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7279319 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3649562 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.2703. Min Act: -0.1700
Data Index: 6075921 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3015. Min Act: -0.1700
Data Index: 2671465 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3015. Min Act: -0.1700
Data Index: 1477870 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.2703. Min Act: -0.1700
Data Index: 461716 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.3015. Min Act: -0.1700
Data Index: 7617673 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.2390. Min Act: -0.1700
Data Index: 4244529 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.2390. Min Act: -0.1700
Data Index: 4405710 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.2078. Min Act: -0.1700
Data Index: 5454860 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1765. Min Act: -0.1700
Data Index: 5787747 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1765. Min Act: -0.1700
Data Index: 3117017 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1453. Min Act: -0.1700
Data Index: 4570635 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1765. Min Act: -0.1700
Data Index: 935283 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1765. Min Act: -0.1700
Data Index: 5384550 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4890. Min Range: -6.4890
Max Act: 6.1765. Min Act: -0.1700
Data Index: 1060901 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19