Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1818. Min Act: -0.1700
Data Index: 6027347 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1503. Min Act: -0.1700
Data Index: 2575220 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1660. Min Act: -0.1700
Data Index: 6048315 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1503. Min Act: -0.1700
Data Index: 6680130 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1345. Min Act: -0.1700
Data Index: 4455186 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1345. Min Act: -0.1700
Data Index: 507582 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1503. Min Act: -0.1700
Data Index: 8629869 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1188. Min Act: -0.1700
Data Index: 6721657 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1030. Min Act: -0.1700
Data Index: 2901801 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1030. Min Act: -0.1700
Data Index: 8701337 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1030. Min Act: -0.1700
Data Index: 266511 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0873. Min Act: -0.1700
Data Index: 1476066 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0873. Min Act: -0.1700
Data Index: 2616559 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1030. Min Act: -0.1700
Data Index: 1316546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.1030. Min Act: -0.1700
Data Index: 4342709 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0873. Min Act: -0.1700
Data Index: 8462907 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0715. Min Act: -0.1700
Data Index: 499647 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0715. Min Act: -0.1700
Data Index: 6812392 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0557. Min Act: -0.1700
Data Index: 2611764 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1818. Min Range: -3.1818
Max Act: 3.0715. Min Act: -0.1700
Data Index: 2611766 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19