Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.7047. Min Act: -0.1700
Data Index: 5924730 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.5601. Min Act: -0.1700
Data Index: 4323342 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.5278. Min Act: -0.1700
Data Index: 3995689 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.5278. Min Act: -0.1700
Data Index: 1888326 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4792. Min Act: -0.1700
Data Index: 3446157 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4630. Min Act: -0.1700
Data Index: 3856626 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4630. Min Act: -0.1700
Data Index: 5556458 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4630. Min Act: -0.1700
Data Index: 1612148 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4630. Min Act: -0.1700
Data Index: 3288027 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4467. Min Act: -0.1700
Data Index: 267684 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4467. Min Act: -0.1700
Data Index: 2420058 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4304. Min Act: -0.1700
Data Index: 5942952 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4142. Min Act: -0.1700
Data Index: 5524747 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4142. Min Act: -0.1700
Data Index: 5546160 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.4142. Min Act: -0.1700
Data Index: 2422427 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.3978. Min Act: -0.1700
Data Index: 8570813 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.3978. Min Act: -0.1700
Data Index: 36737 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.3978. Min Act: -0.1700
Data Index: 124775 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.3815. Min Act: -0.1700
Data Index: 4356236 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7047. Min Range: -2.7047
Max Act: 2.3815. Min Act: -0.1700
Data Index: 1415177 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19