Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2526 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7647. Min Act: -0.1686
Data Index: 1155107 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7388. Min Act: -0.1676
Data Index: 7434934 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7388. Min Act: -0.1698
Data Index: 2184078 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7301. Min Act: -0.1700
Data Index: 5178299 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7301. Min Act: -0.1700
Data Index: 7769726 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7128. Min Act: -0.1621
Data Index: 1987975 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7215. Min Act: -0.1700
Data Index: 2106198 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7301. Min Act: -0.1688
Data Index: 3282890 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.7128. Min Act: -0.1700
Data Index: 6430686 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6955. Min Act: -0.1700
Data Index: 2068210 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6955. Min Act: -0.1678
Data Index: 3078754 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6868. Min Act: -0.1700
Data Index: 7983382 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6868. Min Act: -0.1700
Data Index: 6007029 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6781. Min Act: -0.1700
Data Index: 4050873 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6781. Min Act: -0.1700
Data Index: 724798 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6694. Min Act: -0.1699
Data Index: 4368518 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6607. Min Act: -0.1668
Data Index: 7540342 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6694. Min Act: -0.1700
Data Index: 4605613 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6694. Min Act: -0.1700
Data Index: 1718114 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7647. Min Range: -1.7647
Max Act: 1.6694. Min Act: -0.1590
Data Index: 4032934 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19