Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3363. Min Range: -10.3363
Max Act: 10.3363. Min Act: -0.1700
Data Index: 4220740 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3363. Min Range: -10.3363
Max Act: 10.2738. Min Act: -0.1700
Data Index: 7537475 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3363. Min Range: -10.3363
Max Act: 10.2113. Min Act: -0.1700
Data Index: 8714643 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3363. Min Range: -10.3363
Max Act: 10.0238. Min Act: -0.1700
Data Index: 1375868 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.9613. Min Act: -0.1700
Data Index: 8444777 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8988. Min Act: -0.1700
Data Index: 3562549 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.9613. Min Act: -0.1700
Data Index: 2747263 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.9613. Min Act: -0.1698
Data Index: 994124 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8988. Min Act: -0.1700
Data Index: 2920833 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8988. Min Act: -0.1700
Data Index: 2366508 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.9613. Min Act: -0.1700
Data Index: 387992 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8363. Min Act: -0.1700
Data Index: 5957730 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8363. Min Act: -0.1700
Data Index: 4914659 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8363. Min Act: -0.1700
Data Index: 5028400 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.8363. Min Act: -0.1699
Data Index: 5296680 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.7113. Min Act: -0.1700
Data Index: 1502407 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.7738. Min Act: -0.1700
Data Index: 6506636 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.7738. Min Act: -0.1700
Data Index: 3224623 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.6488. Min Act: -0.1700
Data Index: 5139245 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3363. Min Range: -10.3363
Max Act: 9.7113. Min Act: -0.1700
Data Index: 454252 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19