Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.9559. Min Act: -0.1700
Data Index: 6985808 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.9559. Min Act: -0.1700
Data Index: 7897930 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.8309. Min Act: -0.1700
Data Index: 8371679 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.8621. Min Act: -0.1700
Data Index: 518036 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.7371. Min Act: -0.1700
Data Index: 4215999 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.7996. Min Act: -0.1700
Data Index: 5268256 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.6746. Min Act: -0.1700
Data Index: 8344015 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.6434. Min Act: -0.1700
Data Index: 506940 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.5809. Min Act: -0.1700
Data Index: 5798708 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.5184. Min Act: -0.1700
Data Index: 5215175 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.4559. Min Act: -0.1700
Data Index: 4219177 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.4871. Min Act: -0.1700
Data Index: 5687290 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.4559. Min Act: -0.1700
Data Index: 2316201 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.3934. Min Act: -0.1700
Data Index: 5906329 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.3621. Min Act: -0.1700
Data Index: 2987525 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.3309. Min Act: -0.1700
Data Index: 2300566 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.3934. Min Act: -0.1700
Data Index: 333819 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.2996. Min Act: -0.1700
Data Index: 5940632 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.2996. Min Act: -0.1700
Data Index: 5011811 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9559. Min Range: -7.9559
Max Act: 7.2684. Min Act: -0.1700
Data Index: 4811136 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19