Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1484. Min Range: -9.1484
Max Act: 9.1484. Min Act: -0.1700
Data Index: 1949584 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1484. Min Range: -9.1484
Max Act: 9.0234. Min Act: -0.1700
Data Index: 7114701 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.7109. Min Act: -0.1700
Data Index: 6271249 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.6484. Min Act: -0.1700
Data Index: 349584 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.6484. Min Act: -0.1700
Data Index: 505173 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.6484. Min Act: -0.1700
Data Index: 1078566 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.5234. Min Act: -0.1700
Data Index: 401989 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.3984. Min Act: -0.1700
Data Index: 2248783 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.3359. Min Act: -0.1700
Data Index: 4239842 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.2421. Min Act: -0.1700
Data Index: 2178386 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.2421. Min Act: -0.1700
Data Index: 805597 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.2109. Min Act: -0.1700
Data Index: 8091501 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.2109. Min Act: -0.1700
Data Index: 6959022 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.1484. Min Act: -0.1700
Data Index: 7506234 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.1484. Min Act: -0.1700
Data Index: 4359551 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.1171. Min Act: -0.1700
Data Index: 1097222 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 7475499 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 5515299 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 1015442 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1484. Min Range: -9.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 748015 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19