Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3177 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0117. Min Range: -6.0117
Max Act: 6.0117. Min Act: -0.1700
Data Index: 5856006 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.9804. Min Act: -0.1700
Data Index: 3851465 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.9804. Min Act: -0.1700
Data Index: 5974397 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.9804. Min Act: -0.1700
Data Index: 5282577 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6909560 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8867. Min Act: -0.1700
Data Index: 452055 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8867. Min Act: -0.1700
Data Index: 5084358 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8867. Min Act: -0.1700
Data Index: 7422260 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8867. Min Act: -0.1700
Data Index: 8126210 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8554. Min Act: -0.1700
Data Index: 166479 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8554. Min Act: -0.1700
Data Index: 6406993 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8554. Min Act: -0.1700
Data Index: 689857 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8242. Min Act: -0.1700
Data Index: 5943448 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8242. Min Act: -0.1700
Data Index: 6723314 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8242. Min Act: -0.1700
Data Index: 1457849 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8242. Min Act: -0.1700
Data Index: 1706817 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.8242. Min Act: -0.1700
Data Index: 3580242 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.7929. Min Act: -0.1700
Data Index: 971331 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.7617. Min Act: -0.1700
Data Index: 2565092 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0117. Min Range: -6.0117
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6010570 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19