Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0248. Min Range: -6.0248
Max Act: 6.0248. Min Act: -0.1700
Data Index: 7678475 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.7748. Min Act: -0.1700
Data Index: 5996580 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.6810. Min Act: -0.1700
Data Index: 5996578 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3111820 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.5873. Min Act: -0.1700
Data Index: 3181709 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.5560. Min Act: -0.1700
Data Index: 1964699 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7181678 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7670357 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4935. Min Act: -0.1700
Data Index: 6199873 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1253624 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4623. Min Act: -0.1700
Data Index: 166551 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4623. Min Act: -0.1700
Data Index: 5730896 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4623. Min Act: -0.1700
Data Index: 150644 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4623. Min Act: -0.1700
Data Index: 5005400 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4310. Min Act: -0.1700
Data Index: 361409 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.3998. Min Act: -0.1700
Data Index: 3430024 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.3998. Min Act: -0.1700
Data Index: 100455 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.3998. Min Act: -0.1700
Data Index: 1964701 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.4310. Min Act: -0.1700
Data Index: 6913046 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0248. Min Range: -6.0248
Max Act: 5.3685. Min Act: -0.1700
Data Index: 6056057 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19