Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.8859. Min Act: -0.1700
Data Index: 8693516 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.7609. Min Act: -0.1700
Data Index: 5890161 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.6984. Min Act: -0.1700
Data Index: 2452894 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.6671. Min Act: -0.1700
Data Index: 7852137 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.6359. Min Act: -0.1700
Data Index: 3337879 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.6046. Min Act: -0.1700
Data Index: 6885936 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.5734. Min Act: -0.1700
Data Index: 5330901 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.5734. Min Act: -0.1700
Data Index: 8332970 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.5734. Min Act: -0.1700
Data Index: 3746447 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.5421. Min Act: -0.1700
Data Index: 8105931 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4796. Min Act: -0.1700
Data Index: 3790707 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4484. Min Act: -0.1700
Data Index: 3463128 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4484. Min Act: -0.1700
Data Index: 4203608 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4171. Min Act: -0.1700
Data Index: 57013 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4171. Min Act: -0.1700
Data Index: 6148343 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.3859. Min Act: -0.1700
Data Index: 5649793 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4171. Min Act: -0.1700
Data Index: 4260645 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4484. Min Act: -0.1700
Data Index: 380099 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.4171. Min Act: -0.1700
Data Index: 3679713 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8859. Min Range: -4.8859
Max Act: 4.3859. Min Act: -0.1700
Data Index: 3392244 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19