Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1841 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2219. Min Range: -7.2219
Max Act: 7.2219. Min Act: -0.1700
Data Index: 1732278 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2219. Min Range: -7.2219
Max Act: 7.0656. Min Act: -0.1700
Data Index: 7283227 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2219. Min Range: -7.2219
Max Act: 7.0656. Min Act: -0.1700
Data Index: 3504943 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2219. Min Range: -7.2219
Max Act: 7.0031. Min Act: -0.1700
Data Index: 1767612 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.9719. Min Act: -0.1700
Data Index: 7821617 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.9094. Min Act: -0.1700
Data Index: 2366093 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.9719. Min Act: -0.1700
Data Index: 482786 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.8781. Min Act: -0.1700
Data Index: 4014063 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.8469. Min Act: -0.1700
Data Index: 6072112 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.8469. Min Act: -0.1700
Data Index: 1402905 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.8469. Min Act: -0.1700
Data Index: 7390530 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.8156. Min Act: -0.1700
Data Index: 5652590 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7844. Min Act: -0.1700
Data Index: 2996586 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7844. Min Act: -0.1700
Data Index: 5816131 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7844. Min Act: -0.1700
Data Index: 4517879 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7844. Min Act: -0.1700
Data Index: 4266981 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7531. Min Act: -0.1700
Data Index: 2238601 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.7219. Min Act: -0.1700
Data Index: 1989146 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.6906. Min Act: -0.1700
Data Index: 3954499 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2219. Min Range: -7.2219
Max Act: 6.6594. Min Act: -0.1700
Data Index: 3686452 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19