Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.9715. Min Act: -0.1700
Data Index: 4985009 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.9403. Min Act: -0.1700
Data Index: 4767273 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.8153. Min Act: -0.1700
Data Index: 4932629 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.7840. Min Act: -0.1700
Data Index: 8478365 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.7840. Min Act: -0.1700
Data Index: 8624353 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.7215. Min Act: -0.1700
Data Index: 5946892 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.6590. Min Act: -0.1700
Data Index: 8701667 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5965. Min Act: -0.1700
Data Index: 4523828 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.6590. Min Act: -0.1700
Data Index: 959593 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.6590. Min Act: -0.1700
Data Index: 4539961 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.6278. Min Act: -0.1700
Data Index: 92631 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5965. Min Act: -0.1700
Data Index: 2460952 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5965. Min Act: -0.1700
Data Index: 3218262 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5653. Min Act: -0.1700
Data Index: 5592141 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5340. Min Act: -0.1700
Data Index: 749110 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5340. Min Act: -0.1700
Data Index: 1257626 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5028. Min Act: -0.1700
Data Index: 1119798 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.5028. Min Act: -0.1700
Data Index: 1575188 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.4715. Min Act: -0.1700
Data Index: 5469902 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9715. Min Range: -6.9715
Max Act: 6.4715. Min Act: -0.1700
Data Index: 3248337 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19