Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.3056. Min Act: -0.1700
Data Index: 1067940 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.1806. Min Act: -0.1700
Data Index: 4768053 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.1181. Min Act: -0.1700
Data Index: 327634 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.1493. Min Act: -0.1700
Data Index: 6757440 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.1181. Min Act: -0.1700
Data Index: 8146980 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.1181. Min Act: -0.1700
Data Index: 5543502 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.0868. Min Act: -0.1700
Data Index: 8096910 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.0243. Min Act: -0.1700
Data Index: 7149594 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.0243. Min Act: -0.1700
Data Index: 4132598 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.0243. Min Act: -0.1700
Data Index: 7288135 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3056. Min Range: -4.3056
Max Act: 4.0556. Min Act: -0.1700
Data Index: 5023788 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9931. Min Act: -0.1700
Data Index: 6058656 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9931. Min Act: -0.1700
Data Index: 7921263 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9931. Min Act: -0.1700
Data Index: 2845432 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9618. Min Act: -0.1700
Data Index: 1872407 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9618. Min Act: -0.1700
Data Index: 532294 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9618. Min Act: -0.1700
Data Index: 5021333 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9618. Min Act: -0.1700
Data Index: 7011647 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.8993. Min Act: -0.1700
Data Index: 5391997 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3056. Min Range: -4.3056
Max Act: 3.9305. Min Act: -0.1700
Data Index: 5930756 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19