Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.5472. Min Act: -0.1700
Data Index: 1920944 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4534. Min Act: -0.1700
Data Index: 7000328 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 7999594 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 8018052 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 7349110 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 7961403 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 2319703 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 36595 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2972. Min Act: -0.1700
Data Index: 7557033 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 1794695 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 7287313 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 1625902 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 5031551 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 4013717 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 67019 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 7934665 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 5779030 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 4888259 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 2046769 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2346. Min Act: -0.1700
Data Index: 4531342 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19