Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.9687. Min Act: -0.1700
Data Index: 6679729 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.9177. Min Act: -0.1700
Data Index: 1512999 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.9348. Min Act: -0.1699
Data Index: 4160110 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.9007. Min Act: -0.1700
Data Index: 373548 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8751. Min Act: -0.1700
Data Index: 5193733 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8323. Min Act: -0.1700
Data Index: 7738801 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8237. Min Act: -0.1700
Data Index: 1752306 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8237. Min Act: -0.1700
Data Index: 7516847 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8237. Min Act: -0.1700
Data Index: 1940941 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8151. Min Act: -0.1698
Data Index: 3441468 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8065. Min Act: -0.1700
Data Index: 2320257 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7979. Min Act: -0.1700
Data Index: 5539634 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.8065. Min Act: -0.1694
Data Index: 3115163 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7979. Min Act: -0.1700
Data Index: 235449 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7979. Min Act: -0.1700
Data Index: 8335160 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7893. Min Act: -0.1700
Data Index: 8727535 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7979. Min Act: -0.1700
Data Index: 2003216 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7807. Min Act: -0.1700
Data Index: 2019827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7807. Min Act: -0.1700
Data Index: 3768803 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9687. Min Range: -1.9687
Max Act: 1.7721. Min Act: -0.1700
Data Index: 2950773 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19