Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.9585. Min Act: -0.1700
Data Index: 2908494 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.8335. Min Act: -0.1700
Data Index: 4246907 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.6772. Min Act: -0.1700
Data Index: 7993908 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.4897. Min Act: -0.1700
Data Index: 407378 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.3335. Min Act: -0.1700
Data Index: 4450201 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.3022. Min Act: -0.1700
Data Index: 7282665 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.2710. Min Act: -0.1700
Data Index: 6511746 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1460. Min Act: -0.1694
Data Index: 4697549 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1772. Min Act: -0.1700
Data Index: 2014015 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1460. Min Act: -0.1700
Data Index: 2908491 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1460. Min Act: -0.1700
Data Index: 4704286 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1460. Min Act: -0.1700
Data Index: 5742488 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.1147. Min Act: -0.1700
Data Index: 926771 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.0522. Min Act: -0.1700
Data Index: 3258571 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9585. Min Range: -6.9585
Max Act: 5.9897. Min Act: -0.1700
Data Index: 768371 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.0210. Min Act: -0.1700
Data Index: 3585100 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9585. Min Range: -6.9585
Max Act: 5.9897. Min Act: -0.1698
Data Index: 3761275 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9585. Min Range: -6.9585
Max Act: 5.9585. Min Act: -0.1700
Data Index: 5878455 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9585. Min Range: -6.9585
Max Act: 6.0210. Min Act: -0.1700
Data Index: 2289624 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9585. Min Range: -6.9585
Max Act: 5.9897. Min Act: -0.1700
Data Index: 7045888 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19