Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.4563. Min Act: -0.1700
Data Index: 587338 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.4563. Min Act: -0.1700
Data Index: 5325615 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.3938. Min Act: -0.1700
Data Index: 8377982 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.3938. Min Act: -0.1700
Data Index: 1127196 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.3626. Min Act: -0.1700
Data Index: 8119687 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2688. Min Act: -0.1700
Data Index: 3620766 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2688. Min Act: -0.1700
Data Index: 8295938 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2688. Min Act: -0.1700
Data Index: 4192738 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2688. Min Act: -0.1700
Data Index: 8375425 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2376. Min Act: -0.1700
Data Index: 8295930 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2376. Min Act: -0.1700
Data Index: 1000528 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2063. Min Act: -0.1700
Data Index: 1057714 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.2376. Min Act: -0.1700
Data Index: 2917699 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1438. Min Act: -0.1700
Data Index: 965346 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1438. Min Act: -0.1700
Data Index: 7204223 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1126. Min Act: -0.1700
Data Index: 2576419 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1438. Min Act: -0.1700
Data Index: 3414796 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1438. Min Act: -0.1700
Data Index: 8419819 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1126. Min Act: -0.1700
Data Index: 7881955 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4563. Min Range: -5.4563
Max Act: 5.1126. Min Act: -0.1700
Data Index: 3132347 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19