Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4817 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3966. Min Range: -6.3966
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2394381 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3966. Min Range: -6.3966
Max Act: 6.0529. Min Act: -0.1700
Data Index: 5125837 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3966. Min Range: -6.3966
Max Act: 6.0216. Min Act: -0.1700
Data Index: 6212359 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3966. Min Range: -6.3966
Max Act: 6.0529. Min Act: -0.1700
Data Index: 8280451 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9904. Min Act: -0.1700
Data Index: 2865489 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9591. Min Act: -0.1700
Data Index: 612683 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9591. Min Act: -0.1700
Data Index: 3418190 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9279. Min Act: -0.1700
Data Index: 2932504 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9279. Min Act: -0.1700
Data Index: 58681 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.9279. Min Act: -0.1700
Data Index: 6614356 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8966. Min Act: -0.1700
Data Index: 4736328 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8654. Min Act: -0.1700
Data Index: 83971 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7636761 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8341. Min Act: -0.1700
Data Index: 2713287 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8341. Min Act: -0.1700
Data Index: 1270370 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8029. Min Act: -0.1700
Data Index: 2201845 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.7716. Min Act: -0.1700
Data Index: 7602391 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.8341. Min Act: -0.1700
Data Index: 1766756 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.7716. Min Act: -0.1700
Data Index: 2414290 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3966. Min Range: -6.3966
Max Act: 5.7716. Min Act: -0.1700
Data Index: 5793613 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19