Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1966. Min Range: -15.1966
Max Act: 15.1966. Min Act: -0.1700
Data Index: 6559623 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.8216. Min Act: -0.1700
Data Index: 6130433 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.7591. Min Act: -0.1700
Data Index: 1942017 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.5716. Min Act: -0.1700
Data Index: 6250728 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.5091. Min Act: -0.1700
Data Index: 6756400 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.3216. Min Act: -0.1700
Data Index: 7863156 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.3216. Min Act: -0.1700
Data Index: 7852157 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.3216. Min Act: -0.1700
Data Index: 322679 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.2591. Min Act: -0.1700
Data Index: 3584020 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.1966. Min Act: -0.1700
Data Index: 5084378 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.1341. Min Act: -0.1700
Data Index: 7005530 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.0716. Min Act: -0.1700
Data Index: 4926310 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.0716. Min Act: -0.1700
Data Index: 4235912 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1966. Min Range: -15.1966
Max Act: 14.0091. Min Act: -0.1700
Data Index: 8760834 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.9466. Min Act: -0.1700
Data Index: 1152284 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.9466. Min Act: -0.1700
Data Index: 5409715 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.8841. Min Act: -0.1700
Data Index: 6692213 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.8841. Min Act: -0.1700
Data Index: 1844304 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.8216. Min Act: -0.1700
Data Index: 5668070 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1966. Min Range: -15.1966
Max Act: 13.8216. Min Act: -0.1700
Data Index: 1414560 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19