Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.9531. Min Act: -0.1700
Data Index: 7964972 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.9531. Min Act: -0.1700
Data Index: 8572655 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7968. Min Act: -0.1700
Data Index: 2887929 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 877745 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 4750093 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 3173820 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7656. Min Act: -0.1700
Data Index: 2877064 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7031. Min Act: -0.1700
Data Index: 7715215 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7343. Min Act: -0.1700
Data Index: 1932518 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6718. Min Act: -0.1700
Data Index: 4345713 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.7343. Min Act: -0.1700
Data Index: 3885491 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 1691674 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 433707 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6406. Min Act: -0.1700
Data Index: 7503419 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 446634 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.5781. Min Act: -0.1700
Data Index: 6913818 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 6740798 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.6093. Min Act: -0.1700
Data Index: 7242357 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.5781. Min Act: -0.1700
Data Index: 131946 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9531. Min Range: -4.9531
Max Act: 4.5781. Min Act: -0.1700
Data Index: 4333004 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19