Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4808. Min Range: -8.4808
Max Act: 8.4808. Min Act: -0.1700
Data Index: 3138652 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4808. Min Range: -8.4808
Max Act: 8.3558. Min Act: -0.1700
Data Index: 8242115 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4808. Min Range: -8.4808
Max Act: 8.1683. Min Act: -0.1700
Data Index: 8798965 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4808. Min Range: -8.4808
Max Act: 8.1058. Min Act: -0.1700
Data Index: 4328011 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.9808. Min Act: -0.1700
Data Index: 6123415 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.8558. Min Act: -0.1700
Data Index: 1585229 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.8558. Min Act: -0.1700
Data Index: 6289986 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.8558. Min Act: -0.1700
Data Index: 2830247 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 7349547 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 5180891 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7933. Min Act: -0.1700
Data Index: 7370074 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 3310556 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 7198663 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.6683. Min Act: -0.1700
Data Index: 4907875 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7933. Min Act: -0.1700
Data Index: 1096156 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 8562131 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 1294365 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.7308. Min Act: -0.1700
Data Index: 8725498 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.6683. Min Act: -0.1700
Data Index: 3053718 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4808. Min Range: -8.4808
Max Act: 7.6683. Min Act: -0.1700
Data Index: 6632953 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19