Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2669 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.6284. Min Act: -0.1700
Data Index: 3280079 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 5842233 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.5659. Min Act: -0.1700
Data Index: 8331277 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.4409. Min Act: -0.1700
Data Index: 2660825 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.4409. Min Act: -0.1700
Data Index: 2362306 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.4409. Min Act: -0.1700
Data Index: 4928039 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.3784. Min Act: -0.1700
Data Index: 8735528 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.3159. Min Act: -0.1700
Data Index: 1141561 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.3159. Min Act: -0.1700
Data Index: 4128847 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.3159. Min Act: -0.1700
Data Index: 8276579 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.3159. Min Act: -0.1700
Data Index: 8585963 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.2534. Min Act: -0.1700
Data Index: 5072746 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.2534. Min Act: -0.1700
Data Index: 5745252 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 3030259 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.2534. Min Act: -0.1700
Data Index: 57624 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 2932438 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 820131 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 8085563 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 3897717 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6284. Min Range: -8.6284
Max Act: 8.1909. Min Act: -0.1700
Data Index: 7375890 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19