Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.9425. Min Act: -0.1700
Data Index: 1518170 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.6925. Min Act: -0.1700
Data Index: 4145403 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.6300. Min Act: -0.1700
Data Index: 2154451 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.5675. Min Act: -0.1700
Data Index: 7312370 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.4425. Min Act: -0.1700
Data Index: 5861454 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3800. Min Act: -0.1700
Data Index: 5214096 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3800. Min Act: -0.1700
Data Index: 8008491 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3175. Min Act: -0.1700
Data Index: 8105674 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3175. Min Act: -0.1700
Data Index: 2552713 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 5808472 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3175. Min Act: -0.1700
Data Index: 8743194 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.3175. Min Act: -0.1700
Data Index: 5500322 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 697502 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 8713490 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 3875289 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 678965 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.2550. Min Act: -0.1700
Data Index: 2469231 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.1300. Min Act: -0.1700
Data Index: 3953339 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.1925. Min Act: -0.1700
Data Index: 7921668 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9425. Min Range: -8.9425
Max Act: 8.1300. Min Act: -0.1700
Data Index: 2398036 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19