Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1551. Min Range: -1.1551
Max Act: 1.1551. Min Act: -0.1700
Data Index: 2312616 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1551. Min Range: -1.1551
Max Act: 1.0674. Min Act: -0.1700
Data Index: 4820722 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.9631. Min Act: -0.1700
Data Index: 4558071 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.9287. Min Act: -0.1700
Data Index: 8204766 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.9115. Min Act: -0.1693
Data Index: 2619235 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8944. Min Act: -0.1700
Data Index: 4378948 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8944. Min Act: -0.1700
Data Index: 2312617 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8688. Min Act: -0.1700
Data Index: 2674078 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8518. Min Act: -0.1700
Data Index: 8166657 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8349. Min Act: -0.1700
Data Index: 5489451 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8349. Min Act: -0.1683
Data Index: 7394975 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8180. Min Act: -0.1700
Data Index: 2319508 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8264. Min Act: -0.1700
Data Index: 5791445 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8180. Min Act: -0.1700
Data Index: 2195608 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8264. Min Act: -0.1700
Data Index: 2819039 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8096. Min Act: -0.1700
Data Index: 8261795 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8012. Min Act: -0.1698
Data Index: 7051083 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8012. Min Act: -0.1700
Data Index: 5316538 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8012. Min Act: -0.1700
Data Index: 2474713 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1551. Min Range: -1.1551
Max Act: 0.8096. Min Act: -0.1700
Data Index: 1432640 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19