Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1305. Min Range: -5.1305
Max Act: 5.1305. Min Act: -0.1700
Data Index: 7630901 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.9743. Min Act: -0.1700
Data Index: 1270280 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.9743. Min Act: -0.1700
Data Index: 6751523 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.8180. Min Act: -0.1700
Data Index: 3412295 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7867. Min Act: -0.1700
Data Index: 6618014 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7867. Min Act: -0.1700
Data Index: 776873 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7867. Min Act: -0.1700
Data Index: 8167090 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7555. Min Act: -0.1700
Data Index: 2959753 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7555. Min Act: -0.1700
Data Index: 4719838 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7242. Min Act: -0.1700
Data Index: 5692947 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.7242. Min Act: -0.1700
Data Index: 5087050 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6930. Min Act: -0.1700
Data Index: 1395378 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6930. Min Act: -0.1700
Data Index: 5414755 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 1552685 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 6998430 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 4977767 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 686480 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 3834627 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 4094539 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1305. Min Range: -5.1305
Max Act: 4.6617. Min Act: -0.1700
Data Index: 2903823 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19