Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1969 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1814. Min Range: -6.1814
Max Act: 6.1814. Min Act: -0.1700
Data Index: 4759014 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1814. Min Range: -6.1814
Max Act: 6.1501. Min Act: -0.1700
Data Index: 4744568 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1814. Min Range: -6.1814
Max Act: 6.0876. Min Act: -0.1700
Data Index: 856686 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.9626. Min Act: -0.1700
Data Index: 7313275 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.9001. Min Act: -0.1700
Data Index: 298331 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.8376. Min Act: -0.1700
Data Index: 2674655 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7751. Min Act: -0.1700
Data Index: 5622933 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2195285 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7751. Min Act: -0.1700
Data Index: 4406919 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7751. Min Act: -0.1700
Data Index: 2046474 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7751. Min Act: -0.1700
Data Index: 8702152 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7751. Min Act: -0.1700
Data Index: 6799878 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7439. Min Act: -0.1700
Data Index: 4210752 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7126. Min Act: -0.1700
Data Index: 4709786 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.7126. Min Act: -0.1700
Data Index: 6756103 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.6814. Min Act: -0.1700
Data Index: 2566621 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.6189. Min Act: -0.1700
Data Index: 7630094 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.6814. Min Act: -0.1700
Data Index: 775083 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.6814. Min Act: -0.1700
Data Index: 4180739 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1814. Min Range: -6.1814
Max Act: 5.6814. Min Act: -0.1700
Data Index: 2270643 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19