Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.7342. Min Act: -0.1700
Data Index: 8107506 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6717. Min Act: -0.1700
Data Index: 920129 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.7030. Min Act: -0.1700
Data Index: 8427737 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6404. Min Act: -0.1700
Data Index: 4006222 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6404. Min Act: -0.1700
Data Index: 7527693 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6404. Min Act: -0.1700
Data Index: 5273977 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6091. Min Act: -0.1700
Data Index: 4536317 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.6091. Min Act: -0.1700
Data Index: 8540945 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 2375713 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 7815275 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 480429 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 5962836 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 4328722 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5778. Min Act: -0.1700
Data Index: 4084010 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 7260059 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 7025931 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 3076518 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 5067758 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 6075253 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7342. Min Range: -3.7342
Max Act: 3.5465. Min Act: -0.1700
Data Index: 1053636 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19