Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 898 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.9850. Min Act: -0.1700
Data Index: 4306969 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.8600. Min Act: -0.1700
Data Index: 4214768 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.9225. Min Act: -0.1700
Data Index: 290729 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.8600. Min Act: -0.1700
Data Index: 8754060 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.7350. Min Act: -0.1700
Data Index: 4214766 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.7350. Min Act: -0.1700
Data Index: 3285718 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.7350. Min Act: -0.1700
Data Index: 4214765 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.7350. Min Act: -0.1700
Data Index: 557578 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.7350. Min Act: -0.1700
Data Index: 6149671 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.6100. Min Act: -0.1700
Data Index: 8140192 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.6100. Min Act: -0.1700
Data Index: 906568 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.6100. Min Act: -0.1700
Data Index: 4967339 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.5475. Min Act: -0.1700
Data Index: 4214767 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.5475. Min Act: -0.1700
Data Index: 3933611 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.5475. Min Act: -0.1700
Data Index: 7492435 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.5475. Min Act: -0.1700
Data Index: 1277596 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.4850. Min Act: -0.1700
Data Index: 1509080 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.4850. Min Act: -0.1700
Data Index: 7517445 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.4537. Min Act: -0.1700
Data Index: 916112 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9850. Min Range: -7.9850
Max Act: 7.4537. Min Act: -0.1700
Data Index: 1989272 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19