Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0594. Min Range: -4.0594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 52041 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0594. Min Range: -4.0594
Max Act: 4.0282. Min Act: -0.1700
Data Index: 8363608 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0594. Min Range: -4.0594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 7988409 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9969. Min Act: -0.1700
Data Index: 1636055 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9969. Min Act: -0.1700
Data Index: 6753152 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9969. Min Act: -0.1700
Data Index: 8383280 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9969. Min Act: -0.1700
Data Index: 1626580 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9656. Min Act: -0.1700
Data Index: 3258071 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9344. Min Act: -0.1700
Data Index: 7940021 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9344. Min Act: -0.1700
Data Index: 6634396 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1137796 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9031. Min Act: -0.1700
Data Index: 5990434 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9344. Min Act: -0.1700
Data Index: 2594717 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9031. Min Act: -0.1700
Data Index: 7012722 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9031. Min Act: -0.1700
Data Index: 8403295 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9031. Min Act: -0.1700
Data Index: 4341949 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.8406. Min Act: -0.1700
Data Index: 292078 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.8718. Min Act: -0.1700
Data Index: 6918840 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.8718. Min Act: -0.1700
Data Index: 2268926 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0594. Min Range: -4.0594
Max Act: 3.9031. Min Act: -0.1700
Data Index: 842731 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19