Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.7415. Min Act: -0.1700
Data Index: 2663128 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.7103. Min Act: -0.1700
Data Index: 4434092 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5509739 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.7415. Min Act: -0.1700
Data Index: 6448213 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.7103. Min Act: -0.1700
Data Index: 8505722 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.6790. Min Act: -0.1700
Data Index: 3959022 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.6478. Min Act: -0.1700
Data Index: 8024483 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.6165. Min Act: -0.1700
Data Index: 3673491 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.6165. Min Act: -0.1700
Data Index: 694436 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5853. Min Act: -0.1700
Data Index: 7319358 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 3907399 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5853. Min Act: -0.1700
Data Index: 5353282 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.6165. Min Act: -0.1700
Data Index: 185403 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 7926352 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 973310 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 6448211 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 6262405 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5228. Min Act: -0.1700
Data Index: 8622901 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5228. Min Act: -0.1700
Data Index: 3437478 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7415. Min Range: -5.7415
Max Act: 5.5540. Min Act: -0.1700
Data Index: 6448210 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19