Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1911. Min Act: -0.1699
Data Index: 2794466 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1647. Min Act: -0.1700
Data Index: 6754259 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1471. Min Act: -0.1700
Data Index: 1855145 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1559. Min Act: -0.1700
Data Index: 4543699 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1296. Min Act: -0.1696
Data Index: 98751 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1296. Min Act: -0.1698
Data Index: 7395078 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1208. Min Act: -0.1700
Data Index: 5933833 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1208. Min Act: -0.1700
Data Index: 8476765 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1208. Min Act: -0.1700
Data Index: 3103848 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1208. Min Act: -0.1700
Data Index: 3588489 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1700
Data Index: 7769555 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1698
Data Index: 6415542 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1696
Data Index: 8450069 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1696
Data Index: 8225574 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1697
Data Index: 4655577 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1699
Data Index: 2209682 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1699
Data Index: 8185037 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.0945. Min Act: -0.1691
Data Index: 6831267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.1033. Min Act: -0.1700
Data Index: 2814127 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1911. Min Range: -1.1911
Max Act: 1.0945. Min Act: -0.1700
Data Index: 952933 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19