Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9991. Min Act: -0.1700
Data Index: 5676795 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.8741. Min Act: -0.1700
Data Index: 4573671 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6241. Min Act: -0.1700
Data Index: 920952 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.5928. Min Act: -0.1700
Data Index: 4080506 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6241. Min Act: -0.1700
Data Index: 3713177 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.5303. Min Act: -0.1700
Data Index: 6499553 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4991. Min Act: -0.1700
Data Index: 8792408 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4678. Min Act: -0.1700
Data Index: 6011711 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4678. Min Act: -0.1700
Data Index: 6232816 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4991. Min Act: -0.1700
Data Index: 3036533 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4678. Min Act: -0.1700
Data Index: 6272863 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4366. Min Act: -0.1700
Data Index: 102168 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4053. Min Act: -0.1700
Data Index: 7185782 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4366. Min Act: -0.1700
Data Index: 531848 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4366. Min Act: -0.1700
Data Index: 4219896 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4053. Min Act: -0.1700
Data Index: 7402002 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4053. Min Act: -0.1700
Data Index: 2530359 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.4053. Min Act: -0.1700
Data Index: 7865825 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.3741. Min Act: -0.1700
Data Index: 3743230 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.3741. Min Act: -0.1700
Data Index: 975581 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19