Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3680. Min Range: -6.3680
Max Act: 6.3680. Min Act: -0.1700
Data Index: 5715628 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.9617. Min Act: -0.1700
Data Index: 8791660 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8992. Min Act: -0.1700
Data Index: 4305657 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5597566 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8680. Min Act: -0.1700
Data Index: 5800735 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8367. Min Act: -0.1700
Data Index: 7805533 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8055. Min Act: -0.1700
Data Index: 7279612 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.8367. Min Act: -0.1700
Data Index: 2335595 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7430. Min Act: -0.1700
Data Index: 2500543 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7742. Min Act: -0.1700
Data Index: 6304792 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7742. Min Act: -0.1700
Data Index: 1600878 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7430. Min Act: -0.1700
Data Index: 5090873 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7117. Min Act: -0.1700
Data Index: 177601 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5999563 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.7117. Min Act: -0.1700
Data Index: 1244058 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 5113335 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 5121372 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 851525 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.6492. Min Act: -0.1700
Data Index: 3536398 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3680. Min Range: -6.3680
Max Act: 5.6492. Min Act: -0.1700
Data Index: 1640699 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19