Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4702 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.7625. Min Act: -0.1700
Data Index: 568796 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.3875. Min Act: -0.1700
Data Index: 8302521 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.3562. Min Act: -0.1700
Data Index: 8099965 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.2625. Min Act: -0.1700
Data Index: 1644509 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.2000. Min Act: -0.1700
Data Index: 7565619 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1687. Min Act: -0.1700
Data Index: 4216552 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1687. Min Act: -0.1700
Data Index: 5208235 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1687. Min Act: -0.1700
Data Index: 3831590 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1687. Min Act: -0.1700
Data Index: 4846814 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1375. Min Act: -0.1700
Data Index: 4467262 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1375. Min Act: -0.1700
Data Index: 2625720 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1375. Min Act: -0.1700
Data Index: 2383870 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1687. Min Act: -0.1700
Data Index: 8024367 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1375. Min Act: -0.1700
Data Index: 2464583 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1062. Min Act: -0.1700
Data Index: 4028231 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.0749. Min Act: -0.1700
Data Index: 1489430 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.0749. Min Act: -0.1700
Data Index: 8062472 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1062. Min Act: -0.1700
Data Index: 4041682 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1062. Min Act: -0.1700
Data Index: 3638722 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7625. Min Range: -4.7625
Max Act: 4.1062. Min Act: -0.1700
Data Index: 7388240 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19