Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1669. Min Range: -4.1669
Max Act: 4.1669. Min Act: -0.1700
Data Index: 1781096 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1669. Min Range: -4.1669
Max Act: 4.0418. Min Act: -0.1700
Data Index: 6501514 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9793. Min Act: -0.1700
Data Index: 8598599 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9481. Min Act: -0.1700
Data Index: 8786200 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9481. Min Act: -0.1700
Data Index: 4495256 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9481. Min Act: -0.1700
Data Index: 4569335 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9324. Min Act: -0.1700
Data Index: 2203787 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9012. Min Act: -0.1700
Data Index: 4191674 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9168. Min Act: -0.1700
Data Index: 7411937 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8855. Min Act: -0.1700
Data Index: 7179510 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9012. Min Act: -0.1700
Data Index: 4640802 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.9012. Min Act: -0.1700
Data Index: 2560988 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8855. Min Act: -0.1700
Data Index: 5501787 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8699. Min Act: -0.1700
Data Index: 6768865 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8855. Min Act: -0.1700
Data Index: 5993656 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8855. Min Act: -0.1700
Data Index: 4588034 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8699. Min Act: -0.1700
Data Index: 5168759 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8543. Min Act: -0.1700
Data Index: 7505109 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8543. Min Act: -0.1700
Data Index: 5207857 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1669. Min Range: -4.1669
Max Act: 3.8386. Min Act: -0.1700
Data Index: 1546672 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19