Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6641. Min Act: -0.1700
Data Index: 1307422 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6641. Min Act: -0.1700
Data Index: 6391453 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6329. Min Act: -0.1700
Data Index: 4895427 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6329. Min Act: -0.1700
Data Index: 846310 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6016. Min Act: -0.1700
Data Index: 2260377 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.6016. Min Act: -0.1700
Data Index: 3537580 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.5391. Min Act: -0.1700
Data Index: 4632373 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.4766. Min Act: -0.1700
Data Index: 3138417 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.5078. Min Act: -0.1700
Data Index: 8736811 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.4766. Min Act: -0.1700
Data Index: 4632368 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.4766. Min Act: -0.1700
Data Index: 669890 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 1048260 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 3247312 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 8579030 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 3474153 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 5966877 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3828. Min Act: -0.1700
Data Index: 1543154 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3516. Min Act: -0.1700
Data Index: 2256563 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3516. Min Act: -0.1700
Data Index: 2005998 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6641. Min Range: -4.6641
Max Act: 4.3516. Min Act: -0.1700
Data Index: 1927890 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19