Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2159 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0255. Min Range: -9.0255
Max Act: 9.0255. Min Act: -0.1700
Data Index: 5495765 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.5880. Min Act: -0.1700
Data Index: 7728357 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.5880. Min Act: -0.1700
Data Index: 851210 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.5255. Min Act: -0.1700
Data Index: 4709236 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.5255. Min Act: -0.1700
Data Index: 2171026 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.4630. Min Act: -0.1700
Data Index: 1569266 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.4630. Min Act: -0.1700
Data Index: 26320 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.4005. Min Act: -0.1700
Data Index: 2641265 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.3380. Min Act: -0.1700
Data Index: 7224606 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2755. Min Act: -0.1700
Data Index: 1131677 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2130. Min Act: -0.1700
Data Index: 5785344 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2130. Min Act: -0.1700
Data Index: 6853263 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2130. Min Act: -0.1700
Data Index: 1957441 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2130. Min Act: -0.1700
Data Index: 1388353 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.1505. Min Act: -0.1700
Data Index: 2342874 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.1505. Min Act: -0.1700
Data Index: 5989870 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.1505. Min Act: -0.1700
Data Index: 5190856 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.2130. Min Act: -0.1700
Data Index: 4584911 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.1505. Min Act: -0.1700
Data Index: 3741448 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0255. Min Range: -9.0255
Max Act: 8.1505. Min Act: -0.1700
Data Index: 3881017 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19