Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0901. Min Range: -9.0901
Max Act: 9.0901. Min Act: -0.1700
Data Index: 3456986 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0901. Min Range: -9.0901
Max Act: 9.0901. Min Act: -0.1700
Data Index: 3071727 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0901. Min Range: -9.0901
Max Act: 9.0276. Min Act: -0.1700
Data Index: 3801233 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0901. Min Range: -9.0901
Max Act: 9.0276. Min Act: -0.1700
Data Index: 90427 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9651. Min Act: -0.1700
Data Index: 71120 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9651. Min Act: -0.1700
Data Index: 7653457 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9651. Min Act: -0.1700
Data Index: 8683979 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9651. Min Act: -0.1700
Data Index: 864727 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9026. Min Act: -0.1700
Data Index: 7110284 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9026. Min Act: -0.1700
Data Index: 4232405 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.9651. Min Act: -0.1700
Data Index: 1997553 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 4692890 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.7776. Min Act: -0.1700
Data Index: 5113775 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 6757307 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 6757295 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 357878 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 6207935 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.8401. Min Act: -0.1700
Data Index: 6169490 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.7776. Min Act: -0.1700
Data Index: 7109122 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0901. Min Range: -9.0901
Max Act: 8.7776. Min Act: -0.1700
Data Index: 4029668 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19