Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.8391. Min Act: -0.1700
Data Index: 7202583 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.5891. Min Act: -0.1700
Data Index: 3190866 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.5266. Min Act: -0.1700
Data Index: 2106480 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.3391. Min Act: -0.1700
Data Index: 396833 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.3391. Min Act: -0.1700
Data Index: 3216784 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.2141. Min Act: -0.1700
Data Index: 2415226 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.0891. Min Act: -0.1700
Data Index: 1967582 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.0891. Min Act: -0.1700
Data Index: 8215528 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.0891. Min Act: -0.1700
Data Index: 920736 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8391. Min Range: -10.8391
Max Act: 10.0266. Min Act: -0.1700
Data Index: 6931472 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.9641. Min Act: -0.1700
Data Index: 3148536 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.9016. Min Act: -0.1700
Data Index: 42221 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.9016. Min Act: -0.1700
Data Index: 7352617 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.9016. Min Act: -0.1700
Data Index: 8271994 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 8124490 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 1280230 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 3495977 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 6539384 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 2724178 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8391. Min Range: -10.8391
Max Act: 9.8391. Min Act: -0.1700
Data Index: 6117721 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19