Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 440 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.5562. Min Act: -0.1700
Data Index: 5544669 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 2834402 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.4000. Min Act: -0.1700
Data Index: 2154837 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.4312. Min Act: -0.1700
Data Index: 5293812 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.4312. Min Act: -0.1700
Data Index: 5498566 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3687. Min Act: -0.1700
Data Index: 5762548 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7425303 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7914794 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3687. Min Act: -0.1700
Data Index: 842371 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3062. Min Act: -0.1700
Data Index: 4510988 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3375. Min Act: -0.1700
Data Index: 8805313 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3375. Min Act: -0.1700
Data Index: 5484788 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2750. Min Act: -0.1700
Data Index: 8167192 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.3062. Min Act: -0.1700
Data Index: 7982283 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2437. Min Act: -0.1700
Data Index: 3700396 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2437. Min Act: -0.1700
Data Index: 138759 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2437. Min Act: -0.1700
Data Index: 6170984 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2437. Min Act: -0.1700
Data Index: 2344604 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2437. Min Act: -0.1700
Data Index: 2067872 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5875. Min Range: -5.5875
Max Act: 5.2750. Min Act: -0.1700
Data Index: 865470 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19