Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8670. Min Act: -0.1700
Data Index: 2153272 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8670. Min Act: -0.1700
Data Index: 5498379 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8511. Min Act: -0.1700
Data Index: 4878695 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8193. Min Act: -0.1700
Data Index: 6137583 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8193. Min Act: -0.1700
Data Index: 4169085 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8193. Min Act: -0.1700
Data Index: 6399363 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.8034. Min Act: -0.1700
Data Index: 7799652 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7875. Min Act: -0.1700
Data Index: 5413214 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7715. Min Act: -0.1700
Data Index: 8122223 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7237. Min Act: -0.1700
Data Index: 6615162 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7556. Min Act: -0.1700
Data Index: 534396 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7556. Min Act: -0.1700
Data Index: 424740 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7396. Min Act: -0.1700
Data Index: 2479570 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7237. Min Act: -0.1700
Data Index: 6366677 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7237. Min Act: -0.1700
Data Index: 2312005 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7077. Min Act: -0.1700
Data Index: 1367986 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7077. Min Act: -0.1700
Data Index: 7038206 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7077. Min Act: -0.1700
Data Index: 3221564 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7237. Min Act: -0.1700
Data Index: 5014587 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8670. Min Range: -2.8670
Max Act: 2.7077. Min Act: -0.1700
Data Index: 2084106 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19