Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1727. Min Range: -6.1727
Max Act: 6.1727. Min Act: -0.1700
Data Index: 4561542 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1727. Min Range: -6.1727
Max Act: 6.0164. Min Act: -0.1700
Data Index: 5408001 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.9852. Min Act: -0.1700
Data Index: 4298852 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1727. Min Range: -6.1727
Max Act: 6.0164. Min Act: -0.1700
Data Index: 346920 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.8914. Min Act: -0.1700
Data Index: 1656656 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.8914. Min Act: -0.1700
Data Index: 2488260 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.8289. Min Act: -0.1700
Data Index: 7955625 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7977. Min Act: -0.1700
Data Index: 699884 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.8289. Min Act: -0.1700
Data Index: 4714103 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7977. Min Act: -0.1700
Data Index: 2157142 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7977. Min Act: -0.1700
Data Index: 7731673 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7977. Min Act: -0.1700
Data Index: 5418733 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7664. Min Act: -0.1700
Data Index: 2992041 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7664. Min Act: -0.1700
Data Index: 3124004 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2924722 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7039. Min Act: -0.1700
Data Index: 4298839 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7352. Min Act: -0.1700
Data Index: 8280353 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7039. Min Act: -0.1700
Data Index: 5396132 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.6727. Min Act: -0.1700
Data Index: 208692 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1727. Min Range: -6.1727
Max Act: 5.7352. Min Act: -0.1700
Data Index: 1711736 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19