Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.5519. Min Act: -0.1700
Data Index: 6104294 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.4269. Min Act: -0.1700
Data Index: 7365445 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.1769. Min Act: -0.1700
Data Index: 7077694 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.0831. Min Act: -0.1700
Data Index: 8669868 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.0519. Min Act: -0.1700
Data Index: 3315765 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.0206. Min Act: -0.1700
Data Index: 4195995 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.0206. Min Act: -0.1700
Data Index: 2204047 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5519. Min Range: -6.5519
Max Act: 6.0206. Min Act: -0.1700
Data Index: 3860453 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.9581. Min Act: -0.1700
Data Index: 1149658 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5894613 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.8331. Min Act: -0.1700
Data Index: 5491493 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7706. Min Act: -0.1700
Data Index: 6729765 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.8019. Min Act: -0.1700
Data Index: 6984106 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.8331. Min Act: -0.1700
Data Index: 6234165 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7706. Min Act: -0.1700
Data Index: 7832043 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7394. Min Act: -0.1700
Data Index: 2784651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7706. Min Act: -0.1700
Data Index: 6258534 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7706. Min Act: -0.1700
Data Index: 6558941 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.7706. Min Act: -0.1700
Data Index: 916900 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5519. Min Range: -6.5519
Max Act: 5.6769. Min Act: -0.1700
Data Index: 5545857 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19