Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4012 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.8588. Min Act: -0.1700
Data Index: 122624 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.5775. Min Act: -0.1700
Data Index: 3680474 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.5150. Min Act: -0.1700
Data Index: 4974769 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.4838. Min Act: -0.1700
Data Index: 8456855 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.4838. Min Act: -0.1700
Data Index: 507647 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.4838. Min Act: -0.1700
Data Index: 3500937 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.4213. Min Act: -0.1700
Data Index: 446426 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.3588. Min Act: -0.1700
Data Index: 8461332 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.3275. Min Act: -0.1700
Data Index: 8274114 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2650. Min Act: -0.1700
Data Index: 6507517 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2650. Min Act: -0.1700
Data Index: 7072191 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2338. Min Act: -0.1700
Data Index: 3885706 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2338. Min Act: -0.1700
Data Index: 3300524 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2025. Min Act: -0.1700
Data Index: 3634318 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2338. Min Act: -0.1700
Data Index: 7732843 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2338. Min Act: -0.1700
Data Index: 6375180 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.1713. Min Act: -0.1700
Data Index: 571588 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2025. Min Act: -0.1700
Data Index: 5350468 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.1713. Min Act: -0.1700
Data Index: 5322492 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8588. Min Range: -5.8588
Max Act: 5.2025. Min Act: -0.1700
Data Index: 3497589 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19