Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.7902. Min Act: -0.1700
Data Index: 516665 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.7433. Min Act: -0.1700
Data Index: 5224265 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6964. Min Act: -0.1700
Data Index: 8367277 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6651. Min Act: -0.1700
Data Index: 2144618 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6182. Min Act: -0.1700
Data Index: 1432082 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6182. Min Act: -0.1700
Data Index: 1013152 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 4130437 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6025. Min Act: -0.1700
Data Index: 8733512 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5712. Min Act: -0.1700
Data Index: 3122832 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 2938695 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 2813458 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 2262954 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 2036166 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.6025. Min Act: -0.1700
Data Index: 913566 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5712. Min Act: -0.1700
Data Index: 1453620 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5868. Min Act: -0.1700
Data Index: 7340530 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5555. Min Act: -0.1700
Data Index: 2042780 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5555. Min Act: -0.1700
Data Index: 4209280 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5399. Min Act: -0.1700
Data Index: 2015106 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7902. Min Range: -3.7902
Max Act: 3.5399. Min Act: -0.1700
Data Index: 1427464 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19