Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5384. Min Range: -8.5384
Max Act: 8.5384. Min Act: -0.1700
Data Index: 3676243 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5384. Min Range: -8.5384
Max Act: 8.2884. Min Act: -0.1700
Data Index: 5771326 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5384. Min Range: -8.5384
Max Act: 8.0384. Min Act: -0.1700
Data Index: 7045249 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5384. Min Range: -8.5384
Max Act: 8.0072. Min Act: -0.1700
Data Index: 7909797 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.9447. Min Act: -0.1700
Data Index: 3991954 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.9447. Min Act: -0.1700
Data Index: 2648816 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8822. Min Act: -0.1700
Data Index: 2027420 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8509. Min Act: -0.1700
Data Index: 5441638 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8509. Min Act: -0.1700
Data Index: 7584396 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8822. Min Act: -0.1700
Data Index: 4578516 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7884. Min Act: -0.1700
Data Index: 7173385 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8509. Min Act: -0.1700
Data Index: 8100679 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.8197. Min Act: -0.1700
Data Index: 4495308 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7884. Min Act: -0.1700
Data Index: 3420701 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7884. Min Act: -0.1700
Data Index: 2411188 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7572. Min Act: -0.1700
Data Index: 2494741 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7572. Min Act: -0.1700
Data Index: 2499392 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7572. Min Act: -0.1700
Data Index: 216334 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.6947. Min Act: -0.1700
Data Index: 99244 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5384. Min Range: -8.5384
Max Act: 7.7259. Min Act: -0.1700
Data Index: 6289134 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19