Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.7643. Min Act: -0.1700
Data Index: 7080536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.7331. Min Act: -0.1700
Data Index: 7080538 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.7018. Min Act: -0.1700
Data Index: 4306624 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.7018. Min Act: -0.1700
Data Index: 90457 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.6706. Min Act: -0.1700
Data Index: 2214877 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.6081. Min Act: -0.1700
Data Index: 2171226 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.6081. Min Act: -0.1700
Data Index: 3029124 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5768. Min Act: -0.1700
Data Index: 4374307 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5768. Min Act: -0.1700
Data Index: 7741165 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5768. Min Act: -0.1700
Data Index: 3958680 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5768. Min Act: -0.1700
Data Index: 2550259 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5456. Min Act: -0.1700
Data Index: 2293656 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5456. Min Act: -0.1700
Data Index: 2022790 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5456. Min Act: -0.1700
Data Index: 1141559 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5456. Min Act: -0.1700
Data Index: 4295878 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5143. Min Act: -0.1700
Data Index: 3302691 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5143. Min Act: -0.1700
Data Index: 2280231 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5143. Min Act: -0.1700
Data Index: 6576789 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5143. Min Act: -0.1700
Data Index: 7790765 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7643. Min Range: -4.7643
Max Act: 4.5143. Min Act: -0.1700
Data Index: 934043 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19