Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5427 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7192. Min Range: -7.7192
Max Act: 7.7192. Min Act: -0.1700
Data Index: 4901842 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7192. Min Range: -7.7192
Max Act: 7.0942. Min Act: -0.1700
Data Index: 4790163 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7192. Min Range: -7.7192
Max Act: 7.0317. Min Act: -0.1700
Data Index: 7698984 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.9692. Min Act: -0.1700
Data Index: 534871 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.9067. Min Act: -0.1700
Data Index: 1364285 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.8754. Min Act: -0.1700
Data Index: 7327381 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.8754. Min Act: -0.1700
Data Index: 7207713 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.8129. Min Act: -0.1700
Data Index: 6838671 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.8129. Min Act: -0.1700
Data Index: 3843297 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7817. Min Act: -0.1700
Data Index: 7828623 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7817. Min Act: -0.1700
Data Index: 5342843 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7817. Min Act: -0.1700
Data Index: 6066835 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7504. Min Act: -0.1700
Data Index: 1045284 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7504. Min Act: -0.1700
Data Index: 6543758 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7504. Min Act: -0.1700
Data Index: 1343203 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.7192. Min Act: -0.1700
Data Index: 7108300 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.6879. Min Act: -0.1700
Data Index: 6995505 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.6567. Min Act: -0.1700
Data Index: 6888053 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.6254. Min Act: -0.1700
Data Index: 6841459 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7192. Min Range: -7.7192
Max Act: 6.5942. Min Act: -0.1700
Data Index: 3780649 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19