Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2083 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.3274. Min Act: -0.1700
Data Index: 5395634 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1712. Min Act: -0.1700
Data Index: 7320166 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.1087. Min Act: -0.1700
Data Index: 1509315 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.0774. Min Act: -0.1700
Data Index: 1336474 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.0462. Min Act: -0.1700
Data Index: 5228726 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3274. Min Range: -5.3274
Max Act: 5.0149. Min Act: -0.1700
Data Index: 424733 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9837. Min Act: -0.1700
Data Index: 2779505 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9212. Min Act: -0.1700
Data Index: 6714409 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9212. Min Act: -0.1700
Data Index: 413060 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3044839 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9212. Min Act: -0.1700
Data Index: 8106317 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.9212. Min Act: -0.1700
Data Index: 6719865 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8899. Min Act: -0.1700
Data Index: 138435 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8899. Min Act: -0.1700
Data Index: 6480156 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8899. Min Act: -0.1700
Data Index: 2460947 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8274. Min Act: -0.1700
Data Index: 4746379 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8274. Min Act: -0.1700
Data Index: 6307558 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8274. Min Act: -0.1700
Data Index: 350434 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8274. Min Act: -0.1700
Data Index: 4613283 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3274. Min Range: -5.3274
Max Act: 4.8274. Min Act: -0.1700
Data Index: 4974185 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19