Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.6169. Min Act: -0.1700
Data Index: 436663 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.6169. Min Act: -0.1700
Data Index: 1668801 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.3356. Min Act: -0.1700
Data Index: 7023235 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.3356. Min Act: -0.1700
Data Index: 1037664 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.2106. Min Act: -0.1700
Data Index: 6464473 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4015779 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1481. Min Act: -0.1700
Data Index: 5348931 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1481. Min Act: -0.1700
Data Index: 1179880 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1481. Min Act: -0.1700
Data Index: 3717229 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1555325 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0856. Min Act: -0.1700
Data Index: 2162558 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.1169. Min Act: -0.1700
Data Index: 4327934 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0856. Min Act: -0.1700
Data Index: 3696007 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0856. Min Act: -0.1700
Data Index: 4964130 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1317286 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0544. Min Act: -0.1700
Data Index: 2941893 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6169. Min Range: -6.6169
Max Act: 6.0231. Min Act: -0.1700
Data Index: 4630886 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9919. Min Act: -0.1700
Data Index: 4819008 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9606. Min Act: -0.1700
Data Index: 1725370 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6169. Min Range: -6.6169
Max Act: 5.9606. Min Act: -0.1700
Data Index: 8284755 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19