Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.9294. Min Act: -0.1700
Data Index: 4524930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.9209. Min Act: -0.1700
Data Index: 7091736 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.9124. Min Act: -0.1700
Data Index: 446982 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.9039. Min Act: -0.1700
Data Index: 1800733 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8954. Min Act: -0.1700
Data Index: 607342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8868. Min Act: -0.1700
Data Index: 4855541 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8697. Min Act: -0.1691
Data Index: 3514367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8355. Min Act: -0.1700
Data Index: 7151610 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8355. Min Act: -0.1700
Data Index: 1801126 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8355. Min Act: -0.1700
Data Index: 7471317 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8183. Min Act: -0.1700
Data Index: 7676629 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8097. Min Act: -0.1700
Data Index: 6165652 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8183. Min Act: -0.1700
Data Index: 2880186 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8097. Min Act: -0.1700
Data Index: 8188706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8097. Min Act: -0.1700
Data Index: 4956789 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8011. Min Act: -0.1700
Data Index: 207487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8097. Min Act: -0.1700
Data Index: 6529914 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.7925. Min Act: -0.1700
Data Index: 8759020 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.8011. Min Act: -0.1700
Data Index: 8266228 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9294. Min Range: -1.9294
Max Act: 1.7839. Min Act: -0.1700
Data Index: 5834621 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19