Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1090 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1409191 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.0203. Min Act: -0.1700
Data Index: 5997402 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.0203. Min Act: -0.1700
Data Index: 8073033 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.0203. Min Act: -0.1700
Data Index: 4971156 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 7765855 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 8073032 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 1407792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 5670965 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 467849 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9890. Min Act: -0.1700
Data Index: 6795364 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 7419720 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 1181434 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 7237979 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 4497227 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 4971146 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 3723842 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 7483310 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 8709279 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8953. Min Act: -0.1700
Data Index: 562734 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9265. Min Act: -0.1700
Data Index: 4971157 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19