Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2404. Min Range: -4.2404
Max Act: 4.2404. Min Act: -0.1700
Data Index: 3278898 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2404. Min Range: -4.2404
Max Act: 4.1779. Min Act: -0.1700
Data Index: 3278894 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2404. Min Range: -4.2404
Max Act: 4.1466. Min Act: -0.1700
Data Index: 3278899 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2404. Min Range: -4.2404
Max Act: 4.0216. Min Act: -0.1700
Data Index: 2074031 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.9591. Min Act: -0.1700
Data Index: 3278903 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.8653. Min Act: -0.1700
Data Index: 4757622 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7714. Min Act: -0.1700
Data Index: 7492139 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7402. Min Act: -0.1700
Data Index: 435591 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7714. Min Act: -0.1700
Data Index: 3001241 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7089. Min Act: -0.1700
Data Index: 6729195 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7402. Min Act: -0.1700
Data Index: 6810091 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7402. Min Act: -0.1700
Data Index: 897539 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7402. Min Act: -0.1700
Data Index: 1652913 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.7089. Min Act: -0.1700
Data Index: 3170027 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6932. Min Act: -0.1700
Data Index: 7590273 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6932. Min Act: -0.1700
Data Index: 1660191 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6776. Min Act: -0.1700
Data Index: 8506139 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6619. Min Act: -0.1700
Data Index: 1660192 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6776. Min Act: -0.1700
Data Index: 6206086 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2404. Min Range: -4.2404
Max Act: 3.6619. Min Act: -0.1700
Data Index: 6293755 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19