Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.8355. Min Act: -0.1700
Data Index: 1345977 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.8042. Min Act: -0.1700
Data Index: 4576798 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.7730. Min Act: -0.1700
Data Index: 823144 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.7417. Min Act: -0.1700
Data Index: 6329506 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5855. Min Act: -0.1700
Data Index: 3416038 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5855. Min Act: -0.1700
Data Index: 1056895 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5542. Min Act: -0.1700
Data Index: 5372421 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.5230. Min Act: -0.1700
Data Index: 8416119 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4605. Min Act: -0.1700
Data Index: 690870 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4917. Min Act: -0.1700
Data Index: 8088543 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4292. Min Act: -0.1700
Data Index: 6859372 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4292. Min Act: -0.1700
Data Index: 1445120 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.4292. Min Act: -0.1700
Data Index: 2878034 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3980. Min Act: -0.1700
Data Index: 873570 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3980. Min Act: -0.1700
Data Index: 5367497 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3980. Min Act: -0.1700
Data Index: 4779703 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3667. Min Act: -0.1700
Data Index: 8731288 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3042. Min Act: -0.1700
Data Index: 8003969 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3355. Min Act: -0.1700
Data Index: 2672845 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8355. Min Range: -6.8355
Max Act: 6.3355. Min Act: -0.1700
Data Index: 2800258 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19