Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 351 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.9006. Min Act: -0.1700
Data Index: 3654374 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.8381. Min Act: -0.1700
Data Index: 5014051 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.8068. Min Act: -0.1700
Data Index: 739449 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.8068. Min Act: -0.1700
Data Index: 7694103 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7756. Min Act: -0.1700
Data Index: 8456294 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7131. Min Act: -0.1700
Data Index: 3095690 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7443. Min Act: -0.1700
Data Index: 7694105 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7131. Min Act: -0.1700
Data Index: 5959957 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7131. Min Act: -0.1700
Data Index: 2806889 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5137966 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.7131. Min Act: -0.1700
Data Index: 4585599 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6818. Min Act: -0.1700
Data Index: 322749 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6818. Min Act: -0.1700
Data Index: 4891163 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6506. Min Act: -0.1700
Data Index: 6343167 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6506. Min Act: -0.1700
Data Index: 2346142 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5058256 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6818. Min Act: -0.1700
Data Index: 8456295 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6506. Min Act: -0.1700
Data Index: 1788119 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6193. Min Act: -0.1700
Data Index: 2806887 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9006. Min Range: -4.9006
Max Act: 4.6193. Min Act: -0.1700
Data Index: 5763356 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19