Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2379 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.9291. Min Act: -0.1700
Data Index: 4085570 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 5734283 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 2681029 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1463949 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 4707837 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 2041441 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1040690 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 1082406 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 5455703 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 3852280 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 1267874 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8979. Min Act: -0.1700
Data Index: 3111770 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 110607 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 2515340 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8353. Min Act: -0.1700
Data Index: 93082 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8353. Min Act: -0.1700
Data Index: 481191 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 2444911 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 1197511 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 2443379 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9291. Min Range: -3.9291
Max Act: 3.8666. Min Act: -0.1700
Data Index: 1159111 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19