Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 886 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.6415. Min Act: -0.1700
Data Index: 1226506 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.5478. Min Act: -0.1700
Data Index: 3857009 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.4540. Min Act: -0.1700
Data Index: 3978534 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.4228. Min Act: -0.1700
Data Index: 4301735 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.4228. Min Act: -0.1700
Data Index: 1878353 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3915. Min Act: -0.1700
Data Index: 3978531 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.4228. Min Act: -0.1700
Data Index: 3857007 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3603. Min Act: -0.1700
Data Index: 5410124 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3915. Min Act: -0.1700
Data Index: 2957443 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3915. Min Act: -0.1700
Data Index: 992961 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3603. Min Act: -0.1700
Data Index: 3637950 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3290. Min Act: -0.1700
Data Index: 7893627 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.3290. Min Act: -0.1700
Data Index: 2242797 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2665. Min Act: -0.1700
Data Index: 3857011 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2352. Min Act: -0.1700
Data Index: 6880909 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2352. Min Act: -0.1700
Data Index: 5296787 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2352. Min Act: -0.1700
Data Index: 4520909 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2665. Min Act: -0.1700
Data Index: 4141797 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2352. Min Act: -0.1700
Data Index: 1226508 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6415. Min Range: -4.6415
Max Act: 4.2040. Min Act: -0.1700
Data Index: 1564156 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19