Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0478. Min Range: -5.0478
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8564112 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9853. Min Act: -0.1700
Data Index: 3436966 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 8769489 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 1973057 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 2371845 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.9228. Min Act: -0.1700
Data Index: 179632 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8915. Min Act: -0.1700
Data Index: 7042095 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6834264 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8603. Min Act: -0.1700
Data Index: 4497168 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8603. Min Act: -0.1698
Data Index: 8399441 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8603. Min Act: -0.1700
Data Index: 2392357 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 6409891 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.8290. Min Act: -0.1700
Data Index: 8190619 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7978. Min Act: -0.1700
Data Index: 2717556 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 4245044 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1227803 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7665. Min Act: -0.1700
Data Index: 3135982 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 4152421 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 1771384 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0478. Min Range: -5.0478
Max Act: 4.7353. Min Act: -0.1700
Data Index: 4964520 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19