Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.8735. Min Act: -0.1700
Data Index: 5882844 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.6548. Min Act: -0.1700
Data Index: 3897388 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.6548. Min Act: -0.1700
Data Index: 1121551 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.5923. Min Act: -0.1700
Data Index: 6749866 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.5610. Min Act: -0.1700
Data Index: 1423663 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.4360. Min Act: -0.1700
Data Index: 4323257 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.4360. Min Act: -0.1700
Data Index: 212213 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.4048. Min Act: -0.1700
Data Index: 7922 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.4048. Min Act: -0.1700
Data Index: 2381066 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.2798. Min Act: -0.1700
Data Index: 2325940 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.2173. Min Act: -0.1700
Data Index: 5657936 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1860. Min Act: -0.1700
Data Index: 7414138 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.2173. Min Act: -0.1700
Data Index: 4168825 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.2173. Min Act: -0.1700
Data Index: 6971999 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1548. Min Act: -0.1700
Data Index: 2942250 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1548. Min Act: -0.1700
Data Index: 4778412 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1548. Min Act: -0.1700
Data Index: 1554107 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1548. Min Act: -0.1700
Data Index: 8704983 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.0923. Min Act: -0.1700
Data Index: 4156449 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1235. Min Act: -0.1700
Data Index: 516211 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19