Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.9771. Min Act: -0.1700
Data Index: 6500604 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.9458. Min Act: -0.1700
Data Index: 2630963 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.9771. Min Act: -0.1700
Data Index: 4724790 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.9458. Min Act: -0.1700
Data Index: 8524395 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.9146. Min Act: -0.1700
Data Index: 8524396 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8833. Min Act: -0.1700
Data Index: 3537258 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8833. Min Act: -0.1700
Data Index: 7536871 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8833. Min Act: -0.1700
Data Index: 845529 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8833. Min Act: -0.1700
Data Index: 198526 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8833. Min Act: -0.1700
Data Index: 7261613 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8520. Min Act: -0.1700
Data Index: 2703802 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8520. Min Act: -0.1700
Data Index: 5872268 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8520. Min Act: -0.1700
Data Index: 42196 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.7895. Min Act: -0.1700
Data Index: 1099658 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8208. Min Act: -0.1700
Data Index: 7230337 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8208. Min Act: -0.1700
Data Index: 5087976 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8208. Min Act: -0.1700
Data Index: 1652443 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8520. Min Act: -0.1700
Data Index: 190263 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8208. Min Act: -0.1700
Data Index: 6112072 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9771. Min Range: -3.9771
Max Act: 3.8208. Min Act: -0.1700
Data Index: 1108589 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19