Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4628 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.7310. Min Act: -0.1700
Data Index: 6599631 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.6997. Min Act: -0.1700
Data Index: 4258250 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.6372. Min Act: -0.1700
Data Index: 5406568 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.6060. Min Act: -0.1700
Data Index: 8462516 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.6060. Min Act: -0.1700
Data Index: 5495981 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.6060. Min Act: -0.1700
Data Index: 3751008 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5747. Min Act: -0.1700
Data Index: 1203584 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5435. Min Act: -0.1700
Data Index: 2794481 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5747. Min Act: -0.1700
Data Index: 4870241 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5747. Min Act: -0.1700
Data Index: 737236 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5747. Min Act: -0.1700
Data Index: 2790111 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5435. Min Act: -0.1700
Data Index: 4366433 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5435. Min Act: -0.1700
Data Index: 3174105 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5122. Min Act: -0.1700
Data Index: 7614851 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.5122. Min Act: -0.1700
Data Index: 7694588 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.4810. Min Act: -0.1700
Data Index: 378722 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.4810. Min Act: -0.1700
Data Index: 2434641 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.4810. Min Act: -0.1700
Data Index: 617607 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.4810. Min Act: -0.1700
Data Index: 6455305 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7310. Min Range: -4.7310
Max Act: 4.4810. Min Act: -0.1700
Data Index: 1056006 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19