Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.6242. Min Act: -0.1700
Data Index: 727861 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.5617. Min Act: -0.1700
Data Index: 5531812 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.4367. Min Act: -0.1700
Data Index: 2159315 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.3430. Min Act: -0.1700
Data Index: 5620979 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.2805. Min Act: -0.1700
Data Index: 1294072 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.1555. Min Act: -0.1700
Data Index: 893315 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.1242. Min Act: -0.1700
Data Index: 399606 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.1242. Min Act: -0.1700
Data Index: 990313 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.1242. Min Act: -0.1700
Data Index: 8208550 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.1242. Min Act: -0.1700
Data Index: 8597285 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0929. Min Act: -0.1700
Data Index: 3929924 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0929. Min Act: -0.1700
Data Index: 333073 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0929. Min Act: -0.1700
Data Index: 5135775 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0617. Min Act: -0.1700
Data Index: 878035 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0929. Min Act: -0.1700
Data Index: 7300059 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0304. Min Act: -0.1700
Data Index: 704291 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0617. Min Act: -0.1700
Data Index: 763931 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0304. Min Act: -0.1700
Data Index: 4185372 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6242. Min Range: -4.6242
Max Act: 4.0304. Min Act: -0.1700
Data Index: 2981162 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6242. Min Range: -4.6242
Max Act: 3.9992. Min Act: -0.1700
Data Index: 6347467 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19