Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.6759. Min Act: -0.1700
Data Index: 8824197 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.2384. Min Act: -0.1700
Data Index: 2150602 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.2384. Min Act: -0.1700
Data Index: 8403044 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.1759. Min Act: -0.1700
Data Index: 2341809 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.1759. Min Act: -0.1700
Data Index: 8673994 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.1134. Min Act: -0.1700
Data Index: 6730595 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 607088 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0822. Min Act: -0.1700
Data Index: 8556334 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0197. Min Act: -0.1700
Data Index: 6897497 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 4717577 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 5539845 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0509. Min Act: -0.1700
Data Index: 1064329 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6759. Min Range: -5.6759
Max Act: 5.0197. Min Act: -0.1700
Data Index: 2510911 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.9884. Min Act: -0.1700
Data Index: 1264172 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.9884. Min Act: -0.1700
Data Index: 2675861 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.9884. Min Act: -0.1700
Data Index: 2136815 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.9572. Min Act: -0.1700
Data Index: 8479259 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.8947. Min Act: -0.1700
Data Index: 5418805 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.8634. Min Act: -0.1700
Data Index: 6466472 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6759. Min Range: -5.6759
Max Act: 4.8634. Min Act: -0.1700
Data Index: 616982 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19