Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3349. Min Range: -11.3349
Max Act: 11.3349. Min Act: -0.1700
Data Index: 3098970 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.7099. Min Act: -0.1700
Data Index: 1644483 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.6474. Min Act: -0.1700
Data Index: 4011362 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.6474. Min Act: -0.1698
Data Index: 6855640 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.6474. Min Act: -0.1700
Data Index: 4476368 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.5849. Min Act: -0.1700
Data Index: 213187 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.5224. Min Act: -0.1700
Data Index: 7306482 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.4599. Min Act: -0.1700
Data Index: 7171125 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.3349. Min Act: -0.1700
Data Index: 2854751 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.2724. Min Act: -0.1700
Data Index: 7367690 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.2099. Min Act: -0.1700
Data Index: 8818992 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.2099. Min Act: -0.1700
Data Index: 5022431 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.1474. Min Act: -0.1699
Data Index: 869247 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.1474. Min Act: -0.1700
Data Index: 1332720 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 3530006 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 4841676 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 3958530 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 5288828 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 7400930 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3349. Min Range: -11.3349
Max Act: 10.0849. Min Act: -0.1700
Data Index: 3718026 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19