Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.5453. Min Act: -0.1700
Data Index: 4126851 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4828. Min Act: -0.1700
Data Index: 6050674 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4828. Min Act: -0.1700
Data Index: 1126919 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4828. Min Act: -0.1700
Data Index: 410198 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4203. Min Act: -0.1700
Data Index: 4806696 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4203. Min Act: -0.1700
Data Index: 5928605 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.4828. Min Act: -0.1700
Data Index: 6736396 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1703. Min Act: -0.1700
Data Index: 3630275 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1078. Min Act: -0.1700
Data Index: 3564630 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1078. Min Act: -0.1700
Data Index: 8444704 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.1078. Min Act: -0.1700
Data Index: 5513276 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 8216682 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 2927877 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 349429 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 5401505 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9828. Min Act: -0.1700
Data Index: 3650533 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9203. Min Act: -0.1700
Data Index: 8714796 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5453. Min Range: -8.5453
Max Act: 8.0453. Min Act: -0.1700
Data Index: 6127390 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9828. Min Act: -0.1700
Data Index: 1714635 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5453. Min Range: -8.5453
Max Act: 7.9203. Min Act: -0.1700
Data Index: 879657 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19