Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0900. Min Act: -0.1700
Data Index: 2829522 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5350653 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0588. Min Act: -0.1700
Data Index: 4610328 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0275. Min Act: -0.1700
Data Index: 3483886 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0275. Min Act: -0.1700
Data Index: 8718029 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 6484909 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0275. Min Act: -0.1700
Data Index: 6392177 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0900. Min Range: -5.0900
Max Act: 5.0275. Min Act: -0.1700
Data Index: 6071528 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 2517630 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 2778452 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 7945781 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9650. Min Act: -0.1700
Data Index: 2439543 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 6115792 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 1697013 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 5964712 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 1459795 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 3829595 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 3662147 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9963. Min Act: -0.1700
Data Index: 3550726 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0900. Min Range: -5.0900
Max Act: 4.9650. Min Act: -0.1700
Data Index: 23944 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19