Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3426. Min Range: -7.3426
Max Act: 7.3426. Min Act: -0.1700
Data Index: 2432964 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3426. Min Range: -7.3426
Max Act: 7.0926. Min Act: -0.1700
Data Index: 2801293 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.9676. Min Act: -0.1700
Data Index: 5285364 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.9051. Min Act: -0.1700
Data Index: 528838 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8426. Min Act: -0.1700
Data Index: 8239495 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8426. Min Act: -0.1700
Data Index: 5298183 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8426. Min Act: -0.1700
Data Index: 8134218 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8426. Min Act: -0.1700
Data Index: 2496730 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8113. Min Act: -0.1700
Data Index: 7018649 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2264161 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7801. Min Act: -0.1700
Data Index: 6687161 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7801. Min Act: -0.1700
Data Index: 3764072 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7801. Min Act: -0.1700
Data Index: 7660723 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 4776975 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 2891414 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7020334 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 1485249 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 3442671 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 8760649 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3426. Min Range: -7.3426
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6918086 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19