Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.7123. Min Act: -0.1700
Data Index: 8291745 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.6498. Min Act: -0.1700
Data Index: 1002822 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.5873. Min Act: -0.1700
Data Index: 4887693 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.5873. Min Act: -0.1700
Data Index: 4887708 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.5873. Min Act: -0.1700
Data Index: 1847377 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.2123. Min Act: -0.1700
Data Index: 8696994 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.2123. Min Act: -0.1700
Data Index: 3357535 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.1498. Min Act: -0.1700
Data Index: 1503575 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.2748. Min Act: -0.1700
Data Index: 3249480 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.2123. Min Act: -0.1700
Data Index: 2588211 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.1498. Min Act: -0.1700
Data Index: 4887692 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.1498. Min Act: -0.1700
Data Index: 8619717 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.0873. Min Act: -0.1700
Data Index: 7315000 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.0248. Min Act: -0.1700
Data Index: 3848844 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.1498. Min Act: -0.1700
Data Index: 4887707 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.0248. Min Act: -0.1700
Data Index: 8634162 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7123. Min Range: -12.7123
Max Act: 12.0248. Min Act: -0.1700
Data Index: 3547263 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7123. Min Range: -12.7123
Max Act: 11.9623. Min Act: -0.1700
Data Index: 2711710 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7123. Min Range: -12.7123
Max Act: 11.9623. Min Act: -0.1700
Data Index: 3357546 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7123. Min Range: -12.7123
Max Act: 11.9623. Min Act: -0.1700
Data Index: 3649059 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19