Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8921. Min Act: -0.1700
Data Index: 1100637 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8295. Min Act: -0.1700
Data Index: 6415391 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8608. Min Act: -0.1700
Data Index: 8472263 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8608. Min Act: -0.1700
Data Index: 4432045 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8608. Min Act: -0.1700
Data Index: 1100636 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8608. Min Act: -0.1700
Data Index: 6144788 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 7674502 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8295. Min Act: -0.1700
Data Index: 5808644 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 7341466 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8295. Min Act: -0.1700
Data Index: 6825115 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.8295. Min Act: -0.1700
Data Index: 7216138 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 1537962 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 4899120 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7983. Min Act: -0.1700
Data Index: 8107419 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 6022823 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 303835 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 1100635 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 7868436 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7670. Min Act: -0.1700
Data Index: 8001891 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8921. Min Range: -3.8921
Max Act: 3.7357. Min Act: -0.1700
Data Index: 1630155 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19