Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.8469. Min Act: -0.1700
Data Index: 7590310 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.6282. Min Act: -0.1700
Data Index: 7982395 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.5657. Min Act: -0.1700
Data Index: 8819662 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.5344. Min Act: -0.1700
Data Index: 8181725 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.5344. Min Act: -0.1700
Data Index: 5296342 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.5344. Min Act: -0.1700
Data Index: 7982396 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.4407. Min Act: -0.1700
Data Index: 3127357 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.4407. Min Act: -0.1700
Data Index: 8308969 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.3782. Min Act: -0.1700
Data Index: 5403412 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.3157. Min Act: -0.1700
Data Index: 757078 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2844. Min Act: -0.1700
Data Index: 501906 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3858704 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2532. Min Act: -0.1700
Data Index: 3428435 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4947829 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3138932 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2532. Min Act: -0.1700
Data Index: 370590 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 5485046 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4955617 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1907. Min Act: -0.1700
Data Index: 4370815 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8469. Min Range: -5.8469
Max Act: 5.1907. Min Act: -0.1700
Data Index: 3540197 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19