Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.5220. Min Act: -0.1700
Data Index: 8520723 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.2408. Min Act: -0.1700
Data Index: 300321 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.2720. Min Act: -0.1700
Data Index: 8148564 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.2720. Min Act: -0.1700
Data Index: 2317897 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1470. Min Act: -0.1700
Data Index: 87357 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1470. Min Act: -0.1700
Data Index: 4387199 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1158. Min Act: -0.1700
Data Index: 2407430 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0845. Min Act: -0.1700
Data Index: 7547890 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0533. Min Act: -0.1700
Data Index: 2423270 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0845. Min Act: -0.1700
Data Index: 7321791 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0533. Min Act: -0.1700
Data Index: 175361 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 5111260 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 5971667 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9908. Min Act: -0.1700
Data Index: 6718075 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5922713 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9908. Min Act: -0.1700
Data Index: 2194765 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.8970. Min Act: -0.1700
Data Index: 2534321 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9283. Min Act: -0.1700
Data Index: 4498169 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9283. Min Act: -0.1700
Data Index: 4274431 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.8970. Min Act: -0.1700
Data Index: 7764554 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19