Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.8341. Min Act: -0.1700
Data Index: 8435936 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.7403. Min Act: -0.1700
Data Index: 4746680 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.6466. Min Act: -0.1700
Data Index: 2849078 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.6466. Min Act: -0.1700
Data Index: 5605321 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5841. Min Act: -0.1700
Data Index: 7876967 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5528. Min Act: -0.1700
Data Index: 4916635 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5528. Min Act: -0.1700
Data Index: 2521862 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5528. Min Act: -0.1700
Data Index: 8538670 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5216. Min Act: -0.1700
Data Index: 8510592 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5216. Min Act: -0.1700
Data Index: 6471874 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5216. Min Act: -0.1700
Data Index: 3018448 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 5339088 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 5678230 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.5216. Min Act: -0.1700
Data Index: 6415103 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4278. Min Act: -0.1700
Data Index: 77993 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 8588453 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4278. Min Act: -0.1700
Data Index: 6134259 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 4069575 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 5958211 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8341. Min Range: -6.8341
Max Act: 6.4591. Min Act: -0.1700
Data Index: 3983237 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19