Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1059 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5663. Min Act: -0.1700
Data Index: 6536818 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.6288. Min Act: -0.1700
Data Index: 1700091 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5976. Min Act: -0.1700
Data Index: 7908717 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5351. Min Act: -0.1700
Data Index: 5037308 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5351. Min Act: -0.1700
Data Index: 3952645 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5351. Min Act: -0.1700
Data Index: 8066137 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4726. Min Act: -0.1700
Data Index: 88662 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5038. Min Act: -0.1700
Data Index: 4924780 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5038. Min Act: -0.1700
Data Index: 7186813 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4413. Min Act: -0.1700
Data Index: 7352887 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4726. Min Act: -0.1700
Data Index: 5852418 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4726. Min Act: -0.1700
Data Index: 3693368 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.5038. Min Act: -0.1700
Data Index: 2062163 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4413. Min Act: -0.1700
Data Index: 3531204 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4726. Min Act: -0.1700
Data Index: 8480591 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4101. Min Act: -0.1700
Data Index: 5266622 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4101. Min Act: -0.1700
Data Index: 4924487 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.4413. Min Act: -0.1700
Data Index: 3992638 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.2851. Min Act: -0.1700
Data Index: 993462 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6288. Min Range: -5.6288
Max Act: 5.3788. Min Act: -0.1700
Data Index: 5781045 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19