Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.9051. Min Act: -0.1700
Data Index: 6762920 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.7176. Min Act: -0.1700
Data Index: 5080959 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.7176. Min Act: -0.1700
Data Index: 3547266 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.6863. Min Act: -0.1700
Data Index: 4887689 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6440272 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4887701 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4887704 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5613. Min Act: -0.1700
Data Index: 4712286 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5613. Min Act: -0.1700
Data Index: 6440275 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5613. Min Act: -0.1700
Data Index: 3659447 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 4139547 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 7450778 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 7444280 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 4887699 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 6599373 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5301. Min Act: -0.1700
Data Index: 6599375 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 4580650 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 1606641 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 1527448 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4988. Min Act: -0.1700
Data Index: 2114630 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19