Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.7519. Min Act: -0.1700
Data Index: 1771864 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.6582. Min Act: -0.1700
Data Index: 798454 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.5644. Min Act: -0.1700
Data Index: 3623519 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.3769. Min Act: -0.1700
Data Index: 115469 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.4082. Min Act: -0.1700
Data Index: 1043966 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.3769. Min Act: -0.1700
Data Index: 1071171 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.3769. Min Act: -0.1700
Data Index: 2671641 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.3457. Min Act: -0.1700
Data Index: 5673537 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.2519. Min Act: -0.1700
Data Index: 5301367 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.2207. Min Act: -0.1700
Data Index: 4208165 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1894. Min Act: -0.1700
Data Index: 4800928 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1894. Min Act: -0.1700
Data Index: 5325697 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1582. Min Act: -0.1700
Data Index: 1332612 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1582. Min Act: -0.1700
Data Index: 5369572 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1582. Min Act: -0.1700
Data Index: 638444 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1582. Min Act: -0.1700
Data Index: 1020774 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1269. Min Act: -0.1700
Data Index: 3917435 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1269. Min Act: -0.1700
Data Index: 399963 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1269. Min Act: -0.1700
Data Index: 1236721 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7519. Min Range: -6.7519
Max Act: 6.1269. Min Act: -0.1700
Data Index: 3023509 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19