Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.6328. Min Act: -0.1700
Data Index: 6494303 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.5703. Min Act: -0.1700
Data Index: 1128105 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.5391. Min Act: -0.1700
Data Index: 723212 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4766. Min Act: -0.1700
Data Index: 2465554 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.5078. Min Act: -0.1700
Data Index: 8284270 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4766. Min Act: -0.1700
Data Index: 449964 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4766. Min Act: -0.1700
Data Index: 2800420 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4453. Min Act: -0.1700
Data Index: 3511073 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4141. Min Act: -0.1700
Data Index: 257152 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3828. Min Act: -0.1700
Data Index: 7590737 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1669857 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3828. Min Act: -0.1700
Data Index: 4736763 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3516. Min Act: -0.1700
Data Index: 3735595 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3203. Min Act: -0.1700
Data Index: 5514852 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3828. Min Act: -0.1700
Data Index: 143978 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3516. Min Act: -0.1700
Data Index: 6663043 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.2891. Min Act: -0.1700
Data Index: 5530556 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.2891. Min Act: -0.1700
Data Index: 3339889 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3516. Min Act: -0.1700
Data Index: 318999 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6328. Min Range: -4.6328
Max Act: 4.3516. Min Act: -0.1700
Data Index: 7023443 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19