Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2075. Min Range: -7.2075
Max Act: 7.2075. Min Act: -0.1700
Data Index: 7456100 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2075. Min Range: -7.2075
Max Act: 7.1137. Min Act: -0.1700
Data Index: 6698711 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2075. Min Range: -7.2075
Max Act: 7.0825. Min Act: -0.1700
Data Index: 5567270 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.9262. Min Act: -0.1700
Data Index: 8057917 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.8325. Min Act: -0.1700
Data Index: 2655020 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.8325. Min Act: -0.1700
Data Index: 5515253 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.8325. Min Act: -0.1700
Data Index: 3564945 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.7700. Min Act: -0.1700
Data Index: 4123852 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.7700. Min Act: -0.1700
Data Index: 6992988 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.7700. Min Act: -0.1700
Data Index: 2849810 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.7700. Min Act: -0.1700
Data Index: 6682542 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.7387. Min Act: -0.1700
Data Index: 5567259 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6762. Min Act: -0.1700
Data Index: 2803566 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6762. Min Act: -0.1700
Data Index: 5567260 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6450. Min Act: -0.1700
Data Index: 5307424 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6450. Min Act: -0.1700
Data Index: 8057918 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6450. Min Act: -0.1700
Data Index: 2768312 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6450. Min Act: -0.1700
Data Index: 2768302 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6450. Min Act: -0.1699
Data Index: 1503046 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2075. Min Range: -7.2075
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7610176 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19