Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.9795. Min Act: -0.1700
Data Index: 3972385 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.9286. Min Act: -0.1698
Data Index: 3766227 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.9116. Min Act: -0.1700
Data Index: 6372457 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8774. Min Act: -0.1698
Data Index: 2171618 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8774. Min Act: -0.1700
Data Index: 2089336 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8603. Min Act: -0.1700
Data Index: 3901742 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8432. Min Act: -0.1700
Data Index: 6707597 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8432. Min Act: -0.1694
Data Index: 5537773 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8089. Min Act: -0.1700
Data Index: 2834645 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8260. Min Act: -0.1700
Data Index: 8567243 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8260. Min Act: -0.1700
Data Index: 8567244 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8089. Min Act: -0.1699
Data Index: 5537771 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.8089. Min Act: -0.1699
Data Index: 4623671 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7917. Min Act: -0.1662
Data Index: 4490748 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7917. Min Act: -0.1700
Data Index: 8333838 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7917. Min Act: -0.1700
Data Index: 2591541 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7744. Min Act: -0.1700
Data Index: 5707027 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7917. Min Act: -0.1700
Data Index: 5733815 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7917. Min Act: -0.1700
Data Index: 4121188 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9795. Min Range: -1.9795
Max Act: 1.7744. Min Act: -0.1662
Data Index: 2089335 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19