Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.8117. Min Act: -0.1700
Data Index: 6458388 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.7805. Min Act: -0.1700
Data Index: 4019708 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.7179. Min Act: -0.1700
Data Index: 1131235 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.7179. Min Act: -0.1700
Data Index: 6768279 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.7179. Min Act: -0.1700
Data Index: 8671924 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6866. Min Act: -0.1700
Data Index: 4121348 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6866. Min Act: -0.1700
Data Index: 4785098 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6866. Min Act: -0.1700
Data Index: 6592995 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6553. Min Act: -0.1700
Data Index: 7539071 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6553. Min Act: -0.1700
Data Index: 7361324 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6240. Min Act: -0.1700
Data Index: 8185323 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.6553. Min Act: -0.1700
Data Index: 3061378 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 108526 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 1647132 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 3172405 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 7614674 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 7387072 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 6908129 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5614. Min Act: -0.1700
Data Index: 1643883 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5301. Min Act: -0.1700
Data Index: 3987843 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19