Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2742. Min Range: -6.2742
Max Act: 6.2742. Min Act: -0.1700
Data Index: 8357741 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2742. Min Range: -6.2742
Max Act: 6.0555. Min Act: -0.1700
Data Index: 3071399 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.9305. Min Act: -0.1700
Data Index: 2612469 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.8680. Min Act: -0.1700
Data Index: 463697 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.8367. Min Act: -0.1700
Data Index: 7578797 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7698389 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.6805. Min Act: -0.1700
Data Index: 6141777 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.6492. Min Act: -0.1700
Data Index: 4383530 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.6492. Min Act: -0.1700
Data Index: 2565492 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5867. Min Act: -0.1700
Data Index: 2777373 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5555. Min Act: -0.1700
Data Index: 5984082 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5242. Min Act: -0.1700
Data Index: 5518740 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5555. Min Act: -0.1700
Data Index: 7905060 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5555. Min Act: -0.1700
Data Index: 8348089 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5555. Min Act: -0.1700
Data Index: 2346147 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5555. Min Act: -0.1700
Data Index: 5612227 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.4930. Min Act: -0.1700
Data Index: 4732360 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.4930. Min Act: -0.1700
Data Index: 7194588 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.5242. Min Act: -0.1700
Data Index: 2046057 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2742. Min Range: -6.2742
Max Act: 5.4617. Min Act: -0.1700
Data Index: 1835302 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19