Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.2366. Min Act: -0.1700
Data Index: 8449809 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.2366. Min Act: -0.1700
Data Index: 105126 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1741. Min Act: -0.1700
Data Index: 5378759 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1741. Min Act: -0.1700
Data Index: 1395220 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1116. Min Act: -0.1700
Data Index: 4716564 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1116. Min Act: -0.1700
Data Index: 6178127 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1741. Min Act: -0.1700
Data Index: 6936724 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.1116. Min Act: -0.1700
Data Index: 5309147 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.0491. Min Act: -0.1700
Data Index: 8449812 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.0491. Min Act: -0.1700
Data Index: 2945043 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2366. Min Range: -8.2366
Max Act: 8.0491. Min Act: -0.1700
Data Index: 8043170 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 5968355 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 5603762 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 5461439 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 8221493 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 6136870 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 6769699 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9866. Min Act: -0.1700
Data Index: 3281006 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9241. Min Act: -0.1700
Data Index: 3442616 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2366. Min Range: -8.2366
Max Act: 7.9241. Min Act: -0.1700
Data Index: 5283605 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19