Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.8095. Min Act: -0.1700
Data Index: 3960481 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.5908. Min Act: -0.1700
Data Index: 4334063 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.5908. Min Act: -0.1700
Data Index: 6137668 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4970. Min Act: -0.1700
Data Index: 7132828 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4658. Min Act: -0.1700
Data Index: 1278875 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4970. Min Act: -0.1700
Data Index: 3573703 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4970. Min Act: -0.1700
Data Index: 2580581 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.5283. Min Act: -0.1700
Data Index: 4338097 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2745553 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7165265 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4345. Min Act: -0.1700
Data Index: 2352418 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3773228 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.4033. Min Act: -0.1700
Data Index: 4754868 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2478001 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3720. Min Act: -0.1700
Data Index: 8795573 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3720. Min Act: -0.1700
Data Index: 6417174 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1330627 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3095. Min Act: -0.1700
Data Index: 4900192 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3880168 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8095. Min Range: -6.8095
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7467082 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19