Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4545933 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.9725. Min Act: -0.1700
Data Index: 6465625 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.8162. Min Act: -0.1700
Data Index: 1026098 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.7850. Min Act: -0.1700
Data Index: 1190652 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.7225. Min Act: -0.1700
Data Index: 6108272 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.6912. Min Act: -0.1700
Data Index: 1026099 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.7225. Min Act: -0.1700
Data Index: 8533101 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.6287. Min Act: -0.1700
Data Index: 8784916 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5662. Min Act: -0.1700
Data Index: 5449475 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5975. Min Act: -0.1700
Data Index: 4862693 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5662. Min Act: -0.1700
Data Index: 7067941 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5662. Min Act: -0.1700
Data Index: 2061620 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5662. Min Act: -0.1700
Data Index: 6382255 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5662. Min Act: -0.1700
Data Index: 8515891 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5037. Min Act: -0.1700
Data Index: 2498865 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.5037. Min Act: -0.1700
Data Index: 4778382 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.4725. Min Act: -0.1700
Data Index: 8313375 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.4412. Min Act: -0.1700
Data Index: 604952 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.4412. Min Act: -0.1700
Data Index: 6084444 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9725. Min Range: -6.9725
Max Act: 6.4412. Min Act: -0.1700
Data Index: 5280800 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19