Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9867. Min Act: -0.1700
Data Index: 1848978 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9867. Min Act: -0.1700
Data Index: 5831444 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9242. Min Act: -0.1700
Data Index: 3910425 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.9242. Min Act: -0.1700
Data Index: 305628 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.8305. Min Act: -0.1700
Data Index: 7794063 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7367. Min Act: -0.1700
Data Index: 4780056 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7680. Min Act: -0.1700
Data Index: 8371229 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7055. Min Act: -0.1700
Data Index: 1976092 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.7055. Min Act: -0.1700
Data Index: 251340 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 1557613 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 6416679 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 3701750 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 3364190 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6742. Min Act: -0.1700
Data Index: 2285836 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 8153246 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 2171647 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 5734707 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6430. Min Act: -0.1700
Data Index: 1482141 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6117. Min Act: -0.1700
Data Index: 2202939 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9867. Min Range: -4.9867
Max Act: 4.6117. Min Act: -0.1700
Data Index: 4539106 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19