Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.8651. Min Act: -0.1700
Data Index: 474259 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.8651. Min Act: -0.1700
Data Index: 1190467 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.8338. Min Act: -0.1700
Data Index: 4740882 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.8025. Min Act: -0.1700
Data Index: 4518682 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7712. Min Act: -0.1700
Data Index: 6564633 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7400. Min Act: -0.1700
Data Index: 3997335 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7400. Min Act: -0.1700
Data Index: 5750637 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7400. Min Act: -0.1700
Data Index: 1294810 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 7446744 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7400. Min Act: -0.1700
Data Index: 1086978 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 7350260 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7400. Min Act: -0.1700
Data Index: 640762 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 2054066 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 3067581 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 1561973 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.7087. Min Act: -0.1700
Data Index: 7112563 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.6774. Min Act: -0.1700
Data Index: 5425666 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.6774. Min Act: -0.1700
Data Index: 3890682 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.6774. Min Act: -0.1700
Data Index: 1651692 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8651. Min Range: -3.8651
Max Act: 3.6774. Min Act: -0.1700
Data Index: 1770586 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19