Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4997 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.2915. Min Act: -0.1700
Data Index: 6560018 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.1665. Min Act: -0.1700
Data Index: 3926266 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.1353. Min Act: -0.1700
Data Index: 1623610 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.1040. Min Act: -0.1700
Data Index: 2849578 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.9790. Min Act: -0.1700
Data Index: 957867 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.0103. Min Act: -0.1700
Data Index: 520521 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.9165. Min Act: -0.1700
Data Index: 6590802 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8540. Min Act: -0.1700
Data Index: 2841575 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7915. Min Act: -0.1700
Data Index: 502575 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8228. Min Act: -0.1700
Data Index: 5143788 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7603. Min Act: -0.1700
Data Index: 1529884 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7915. Min Act: -0.1700
Data Index: 4060221 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 3026164 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 5045516 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 274825 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.6978. Min Act: -0.1700
Data Index: 5789050 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.6978. Min Act: -0.1700
Data Index: 4579285 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.6665. Min Act: -0.1700
Data Index: 3026167 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.6353. Min Act: -0.1700
Data Index: 6991582 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.6353. Min Act: -0.1700
Data Index: 6556706 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19