Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.4376. Min Act: -0.1700
Data Index: 8518731 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.3438. Min Act: -0.1700
Data Index: 6431411 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2813. Min Act: -0.1700
Data Index: 2951123 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2501. Min Act: -0.1700
Data Index: 6148817 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2501. Min Act: -0.1700
Data Index: 547920 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5720382 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2501. Min Act: -0.1700
Data Index: 3704830 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5368270 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2188. Min Act: -0.1700
Data Index: 2403186 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2188. Min Act: -0.1700
Data Index: 8646720 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.2188. Min Act: -0.1700
Data Index: 4002429 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4338856 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1876. Min Act: -0.1700
Data Index: 6285162 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1876. Min Act: -0.1700
Data Index: 7987751 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1876. Min Act: -0.1700
Data Index: 6013727 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1563. Min Act: -0.1700
Data Index: 4430995 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1563. Min Act: -0.1700
Data Index: 2366245 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1563. Min Act: -0.1700
Data Index: 5772030 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.1251. Min Act: -0.1700
Data Index: 1974971 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4376. Min Range: -5.4376
Max Act: 5.0938. Min Act: -0.1700
Data Index: 1578110 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19