Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.9488. Min Act: -0.1700
Data Index: 8640466 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.9488. Min Act: -0.1700
Data Index: 5393717 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.8238. Min Act: -0.1700
Data Index: 5050008 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.7300. Min Act: -0.1700
Data Index: 1762951 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.6988. Min Act: -0.1700
Data Index: 6284995 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.6050. Min Act: -0.1700
Data Index: 4698703 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.6363. Min Act: -0.1700
Data Index: 767984 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.6050. Min Act: -0.1700
Data Index: 7332722 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.4800. Min Act: -0.1700
Data Index: 944238 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.4488. Min Act: -0.1700
Data Index: 8320978 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.4175. Min Act: -0.1700
Data Index: 8396122 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.4175. Min Act: -0.1700
Data Index: 4505995 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3863. Min Act: -0.1700
Data Index: 2387056 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3863. Min Act: -0.1700
Data Index: 7621771 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3863. Min Act: -0.1700
Data Index: 3388476 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3550. Min Act: -0.1700
Data Index: 1786072 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3550. Min Act: -0.1700
Data Index: 3626673 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3550. Min Act: -0.1700
Data Index: 8434662 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3238. Min Act: -0.1700
Data Index: 677080 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9488. Min Range: -6.9488
Max Act: 6.3238. Min Act: -0.1700
Data Index: 7747682 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19