Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0132. Min Range: -5.0132
Max Act: 5.0132. Min Act: -0.1700
Data Index: 8046386 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.7319. Min Act: -0.1700
Data Index: 7719783 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.7319. Min Act: -0.1700
Data Index: 3132311 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.7007. Min Act: -0.1700
Data Index: 6979366 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.6069. Min Act: -0.1700
Data Index: 4839058 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5444. Min Act: -0.1700
Data Index: 2528155 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1635049 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5444. Min Act: -0.1700
Data Index: 7218976 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1158817 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5132. Min Act: -0.1700
Data Index: 5561564 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.5132. Min Act: -0.1700
Data Index: 2360291 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4819. Min Act: -0.1700
Data Index: 5837080 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4819. Min Act: -0.1700
Data Index: 7497708 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4507. Min Act: -0.1700
Data Index: 2431594 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4507. Min Act: -0.1700
Data Index: 206432 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1806897 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.4194. Min Act: -0.1700
Data Index: 7923809 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.3882. Min Act: -0.1700
Data Index: 1031482 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.3882. Min Act: -0.1700
Data Index: 2238060 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0132. Min Range: -5.0132
Max Act: 4.3882. Min Act: -0.1700
Data Index: 6546070 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19