Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.1895. Min Act: -0.1700
Data Index: 1914020 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.1270. Min Act: -0.1700
Data Index: 8431769 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0332. Min Act: -0.1700
Data Index: 2065666 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0645. Min Act: -0.1700
Data Index: 2652740 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0645. Min Act: -0.1700
Data Index: 2339444 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0645. Min Act: -0.1700
Data Index: 4037999 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0645. Min Act: -0.1700
Data Index: 424458 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0332. Min Act: -0.1700
Data Index: 6918466 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0332. Min Act: -0.1700
Data Index: 3114591 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0332. Min Act: -0.1699
Data Index: 5674059 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 3121563 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0020. Min Act: -0.1700
Data Index: 3385325 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.0020. Min Act: -0.1700
Data Index: 437354 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 5011411 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9395. Min Act: -0.1700
Data Index: 7897690 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 6056963 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 5475735 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 7887913 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9395. Min Act: -0.1700
Data Index: 383662 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.9395. Min Act: -0.1700
Data Index: 1258908 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19