Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.3314. Min Act: -0.1700
Data Index: 4853500 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1752. Min Act: -0.1700
Data Index: 2846323 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 8583282 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 3079576 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 1420510 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 6022185 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 188137 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.1127. Min Act: -0.1700
Data Index: 2934005 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8689586 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8283742 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4605319 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0189. Min Act: -0.1700
Data Index: 2208460 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0189. Min Act: -0.1700
Data Index: 6952779 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0189. Min Act: -0.1700
Data Index: 3353853 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5955547 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3314. Min Range: -6.3314
Max Act: 6.0189. Min Act: -0.1700
Data Index: 3113673 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3314. Min Range: -6.3314
Max Act: 5.9564. Min Act: -0.1700
Data Index: 4166641 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3314. Min Range: -6.3314
Max Act: 5.9877. Min Act: -0.1700
Data Index: 3516366 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3314. Min Range: -6.3314
Max Act: 5.9877. Min Act: -0.1700
Data Index: 1619490 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3314. Min Range: -6.3314
Max Act: 5.9877. Min Act: -0.1700
Data Index: 1927756 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19