Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.9329. Min Act: -0.1700
Data Index: 2100634 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.9641. Min Act: -0.1700
Data Index: 1562355 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.9016. Min Act: -0.1700
Data Index: 5720375 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.8391. Min Act: -0.1700
Data Index: 1356474 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.8391. Min Act: -0.1700
Data Index: 3498974 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.8391. Min Act: -0.1700
Data Index: 1856337 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.8391. Min Act: -0.1700
Data Index: 2586081 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7454. Min Act: -0.1700
Data Index: 2756162 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7454. Min Act: -0.1700
Data Index: 6220142 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7766. Min Act: -0.1700
Data Index: 8393804 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7141. Min Act: -0.1700
Data Index: 3695240 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2167310 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2706496 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2909032 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.6829. Min Act: -0.1700
Data Index: 798348 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.6829. Min Act: -0.1700
Data Index: 7891463 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.6829. Min Act: -0.1700
Data Index: 7220482 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6869792 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.6829. Min Act: -0.1700
Data Index: 1309454 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9641. Min Range: -5.9641
Max Act: 5.6516. Min Act: -0.1700
Data Index: 2538612 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19