Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4717 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.2373. Min Act: -0.1700
Data Index: 1636473 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.0484. Min Act: -0.1700
Data Index: 8355749 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9377. Min Act: -0.1700
Data Index: 2590946 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9536. Min Act: -0.1700
Data Index: 6579942 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9536. Min Act: -0.1700
Data Index: 3477884 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9377. Min Act: -0.1700
Data Index: 4221552 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9219. Min Act: -0.1700
Data Index: 7891231 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9219. Min Act: -0.1700
Data Index: 90003 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9377. Min Act: -0.1700
Data Index: 8354641 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8902. Min Act: -0.1700
Data Index: 8436593 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8743. Min Act: -0.1700
Data Index: 5487245 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 3773625 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 5979929 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 1068742 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 3601393 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7948. Min Act: -0.1700
Data Index: 7536823 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7789. Min Act: -0.1700
Data Index: 5317996 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7948. Min Act: -0.1700
Data Index: 5468454 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 1713830 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 1305905 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19