Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.2488. Min Act: -0.1700
Data Index: 3685854 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.2488. Min Act: -0.1700
Data Index: 3037914 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.2174. Min Act: -0.1700
Data Index: 1010342 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.1072. Min Act: -0.1700
Data Index: 6238325 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.0599. Min Act: -0.1700
Data Index: 645621 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.0126. Min Act: -0.1700
Data Index: 8830737 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9652. Min Act: -0.1700
Data Index: 7706814 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9968. Min Act: -0.1700
Data Index: 1420376 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2488. Min Range: -3.2488
Max Act: 3.0284. Min Act: -0.1700
Data Index: 5697320 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9810. Min Act: -0.1700
Data Index: 56594 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9810. Min Act: -0.1700
Data Index: 4482708 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9810. Min Act: -0.1700
Data Index: 4706993 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9968. Min Act: -0.1700
Data Index: 5646156 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9652. Min Act: -0.1700
Data Index: 4101513 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9493. Min Act: -0.1700
Data Index: 5989263 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9968. Min Act: -0.1700
Data Index: 3697912 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9810. Min Act: -0.1700
Data Index: 4659820 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9810. Min Act: -0.1700
Data Index: 8742488 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9335. Min Act: -0.1700
Data Index: 4559847 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2488. Min Range: -3.2488
Max Act: 2.9652. Min Act: -0.1700
Data Index: 707611 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19