Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1756 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.3305. Min Act: -0.1700
Data Index: 2636549 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.2680. Min Act: -0.1700
Data Index: 1113945 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.2367. Min Act: -0.1700
Data Index: 8029331 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.2055. Min Act: -0.1700
Data Index: 8277104 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.2055. Min Act: -0.1700
Data Index: 7850751 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.2055. Min Act: -0.1700
Data Index: 6314409 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.1742. Min Act: -0.1700
Data Index: 1113937 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.1430. Min Act: -0.1700
Data Index: 1250511 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.0805. Min Act: -0.1700
Data Index: 2001654 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.0805. Min Act: -0.1700
Data Index: 6069111 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3305. Min Range: -6.3305
Max Act: 6.0180. Min Act: -0.1700
Data Index: 7088722 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.9867. Min Act: -0.1700
Data Index: 3614035 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.9242. Min Act: -0.1700
Data Index: 2852577 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.9242. Min Act: -0.1700
Data Index: 2471267 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.9242. Min Act: -0.1700
Data Index: 8734289 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.9242. Min Act: -0.1700
Data Index: 5608104 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.8930. Min Act: -0.1700
Data Index: 7242690 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.8930. Min Act: -0.1700
Data Index: 6291498 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.8930. Min Act: -0.1700
Data Index: 3331757 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3305. Min Range: -6.3305
Max Act: 5.8930. Min Act: -0.1700
Data Index: 2840295 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19