Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.5387. Min Act: -0.1700
Data Index: 4291995 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4760. Min Act: -0.1700
Data Index: 8200959 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4603. Min Act: -0.1700
Data Index: 3460655 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4290. Min Act: -0.1700
Data Index: 4543877 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4133. Min Act: -0.1700
Data Index: 8062848 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4133. Min Act: -0.1700
Data Index: 6205959 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.4133. Min Act: -0.1700
Data Index: 6921201 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3976. Min Act: -0.1700
Data Index: 3749063 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3976. Min Act: -0.1700
Data Index: 7679686 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3663. Min Act: -0.1700
Data Index: 1452067 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3663. Min Act: -0.1700
Data Index: 8081171 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3506. Min Act: -0.1700
Data Index: 7218487 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3506. Min Act: -0.1700
Data Index: 7064729 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1376347 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3506. Min Act: -0.1700
Data Index: 1171808 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3349. Min Act: -0.1700
Data Index: 828904 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3035. Min Act: -0.1700
Data Index: 2481112 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3035. Min Act: -0.1700
Data Index: 5674053 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3035. Min Act: -0.1700
Data Index: 6749875 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5387. Min Range: -3.5387
Max Act: 3.3035. Min Act: -0.1700
Data Index: 3989723 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19