Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5291 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.2508. Min Act: -0.1700
Data Index: 7394516 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.1258. Min Act: -0.1700
Data Index: 7014034 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2508. Min Range: -5.2508
Max Act: 5.0321. Min Act: -0.1700
Data Index: 228696 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9383. Min Act: -0.1700
Data Index: 6280900 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9383. Min Act: -0.1700
Data Index: 4084436 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9383. Min Act: -0.1700
Data Index: 5732312 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.9071. Min Act: -0.1700
Data Index: 5119473 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8758. Min Act: -0.1700
Data Index: 779318 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8758. Min Act: -0.1700
Data Index: 1192837 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8758. Min Act: -0.1700
Data Index: 906552 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8446. Min Act: -0.1700
Data Index: 2045518 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.8133. Min Act: -0.1700
Data Index: 8230048 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7821. Min Act: -0.1700
Data Index: 3834760 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7508. Min Act: -0.1700
Data Index: 5857138 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7821. Min Act: -0.1700
Data Index: 3362808 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7508. Min Act: -0.1700
Data Index: 681345 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7196. Min Act: -0.1700
Data Index: 2535230 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7196. Min Act: -0.1700
Data Index: 5296351 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.7196. Min Act: -0.1700
Data Index: 320439 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2508. Min Range: -5.2508
Max Act: 4.6883. Min Act: -0.1700
Data Index: 5153364 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19