Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.2818. Min Act: -0.1700
Data Index: 360501 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.2190. Min Act: -0.1700
Data Index: 2843770 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.2190. Min Act: -0.1700
Data Index: 7713812 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.2032. Min Act: -0.1700
Data Index: 7702744 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1875. Min Act: -0.1700
Data Index: 6341845 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1718. Min Act: -0.1700
Data Index: 3379301 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1560. Min Act: -0.1700
Data Index: 3664689 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1403. Min Act: -0.1700
Data Index: 4246603 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1560. Min Act: -0.1700
Data Index: 7868624 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1403. Min Act: -0.1700
Data Index: 8720708 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.1088. Min Act: -0.1700
Data Index: 5953002 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0930. Min Act: -0.1700
Data Index: 2805558 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1221914 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0615. Min Act: -0.1700
Data Index: 4664405 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0615. Min Act: -0.1700
Data Index: 648950 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0457. Min Act: -0.1700
Data Index: 116874 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0457. Min Act: -0.1700
Data Index: 3961155 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0457. Min Act: -0.1700
Data Index: 1354528 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0457. Min Act: -0.1700
Data Index: 8303480 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2818. Min Range: -3.2818
Max Act: 3.0457. Min Act: -0.1700
Data Index: 7061928 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19