Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.6307. Min Act: -0.1700
Data Index: 3847862 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.5057. Min Act: -0.1700
Data Index: 5945897 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.1307. Min Act: -0.1700
Data Index: 5557661 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.2557. Min Act: -0.1700
Data Index: 4683810 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.0057. Min Act: -0.1700
Data Index: 495854 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.0057. Min Act: -0.1700
Data Index: 2039069 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.0057. Min Act: -0.1700
Data Index: 2482192 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.6307. Min Range: -16.6307
Max Act: 16.0057. Min Act: -0.1700
Data Index: 3526836 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.8807. Min Act: -0.1700
Data Index: 7048302 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.8807. Min Act: -0.1700
Data Index: 7735336 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.7557. Min Act: -0.1700
Data Index: 5948435 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.7557. Min Act: -0.1700
Data Index: 1324573 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.7557. Min Act: -0.1700
Data Index: 6790393 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 5620134 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 5574978 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 4265856 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 8736728 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 4013578 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.6307. Min Act: -0.1700
Data Index: 1011334 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.6307. Min Range: -16.6307
Max Act: 15.5682. Min Act: -0.1700
Data Index: 5425023 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19