Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1609. Min Range: -6.1609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 6121076 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1609. Min Range: -6.1609
Max Act: 6.0046. Min Act: -0.1700
Data Index: 328616 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1609. Min Range: -6.1609
Max Act: 6.0046. Min Act: -0.1700
Data Index: 4645507 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.9421. Min Act: -0.1700
Data Index: 5134115 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.9734. Min Act: -0.1700
Data Index: 8093719 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.9421. Min Act: -0.1700
Data Index: 1860659 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8796. Min Act: -0.1700
Data Index: 3730577 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8796. Min Act: -0.1700
Data Index: 7463828 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.9109. Min Act: -0.1700
Data Index: 4252699 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8484. Min Act: -0.1700
Data Index: 7558640 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8171. Min Act: -0.1700
Data Index: 7356075 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8171. Min Act: -0.1700
Data Index: 8710529 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.8171. Min Act: -0.1700
Data Index: 3691778 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.7234. Min Act: -0.1700
Data Index: 8055270 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.7234. Min Act: -0.1700
Data Index: 6753407 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.6921. Min Act: -0.1700
Data Index: 1292674 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.7234. Min Act: -0.1700
Data Index: 4252700 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.6609. Min Act: -0.1700
Data Index: 4083782 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.6921. Min Act: -0.1700
Data Index: 1688566 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1609. Min Range: -6.1609
Max Act: 5.6921. Min Act: -0.1700
Data Index: 5847389 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19