Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 770 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.7526. Min Act: -0.1700
Data Index: 375761 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6887. Min Act: -0.1700
Data Index: 6628571 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6887. Min Act: -0.1700
Data Index: 3830291 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6887. Min Act: -0.1700
Data Index: 8724890 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6726. Min Act: -0.1700
Data Index: 1146285 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6406. Min Act: -0.1700
Data Index: 1299451 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6245. Min Act: -0.1700
Data Index: 2184271 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.6245. Min Act: -0.1700
Data Index: 2362380 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5762. Min Act: -0.1700
Data Index: 1868098 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5923. Min Act: -0.1700
Data Index: 6752230 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5923. Min Act: -0.1700
Data Index: 7318067 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5762. Min Act: -0.1700
Data Index: 6716192 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5601. Min Act: -0.1700
Data Index: 909044 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5601. Min Act: -0.1700
Data Index: 5524303 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5439. Min Act: -0.1700
Data Index: 3743798 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5278. Min Act: -0.1700
Data Index: 3090856 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5439. Min Act: -0.1700
Data Index: 1875106 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5439. Min Act: -0.1700
Data Index: 7843498 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4904896 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7526. Min Range: -2.7526
Max Act: 2.5278. Min Act: -0.1700
Data Index: 1875112 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19