Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.9829. Min Act: -0.1700
Data Index: 4539453 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.4829. Min Act: -0.1700
Data Index: 2578532 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.3579. Min Act: -0.1700
Data Index: 2942952 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.3579. Min Act: -0.1700
Data Index: 4118687 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.2954. Min Act: -0.1700
Data Index: 3335379 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.2329. Min Act: -0.1700
Data Index: 6305097 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.2329. Min Act: -0.1700
Data Index: 8343224 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1704. Min Act: -0.1700
Data Index: 289831 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1704. Min Act: -0.1700
Data Index: 1258647 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1704. Min Act: -0.1700
Data Index: 2760692 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1704. Min Act: -0.1700
Data Index: 2143147 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1079. Min Act: -0.1700
Data Index: 7372350 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.1079. Min Act: -0.1700
Data Index: 3955207 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.0454. Min Act: -0.1700
Data Index: 1199103 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.0454. Min Act: -0.1700
Data Index: 3244219 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.0454. Min Act: -0.1700
Data Index: 8153031 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9829. Min Range: -11.9829
Max Act: 11.0454. Min Act: -0.1700
Data Index: 4358423 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9829. Min Range: -11.9829
Max Act: 10.9829. Min Act: -0.1700
Data Index: 174027 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9829. Min Range: -11.9829
Max Act: 10.9829. Min Act: -0.1700
Data Index: 4481363 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9829. Min Range: -11.9829
Max Act: 10.9829. Min Act: -0.1700
Data Index: 6814547 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19