Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.1540. Min Act: -0.1700
Data Index: 4899626 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.1540. Min Act: -0.1700
Data Index: 7997945 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.1228. Min Act: -0.1700
Data Index: 7420091 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.0915. Min Act: -0.1700
Data Index: 916674 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.0915. Min Act: -0.1700
Data Index: 4899628 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1540. Min Range: -6.1540
Max Act: 6.0603. Min Act: -0.1700
Data Index: 3647623 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.9353. Min Act: -0.1700
Data Index: 3729145 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.9040. Min Act: -0.1700
Data Index: 5064811 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.9040. Min Act: -0.1700
Data Index: 15808 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.8415. Min Act: -0.1700
Data Index: 7423569 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.8415. Min Act: -0.1700
Data Index: 8605412 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.7478. Min Act: -0.1700
Data Index: 4941682 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.7165. Min Act: -0.1700
Data Index: 5810314 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6853. Min Act: -0.1700
Data Index: 7321956 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6853. Min Act: -0.1700
Data Index: 4412815 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6540. Min Act: -0.1700
Data Index: 6259154 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6540. Min Act: -0.1700
Data Index: 1708933 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6228. Min Act: -0.1700
Data Index: 8301539 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.6228. Min Act: -0.1700
Data Index: 2338880 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1540. Min Range: -6.1540
Max Act: 5.5915. Min Act: -0.1700
Data Index: 7731952 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19