Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.6079. Min Act: -0.1700
Data Index: 1014914 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.5766. Min Act: -0.1700
Data Index: 503581 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.5454. Min Act: -0.1700
Data Index: 912381 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.5141. Min Act: -0.1700
Data Index: 3160036 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4828. Min Act: -0.1700
Data Index: 1031782 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4516. Min Act: -0.1700
Data Index: 8099251 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4516. Min Act: -0.1700
Data Index: 7965964 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4203. Min Act: -0.1700
Data Index: 4037423 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4203. Min Act: -0.1700
Data Index: 4906347 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4516. Min Act: -0.1700
Data Index: 4746879 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4203. Min Act: -0.1700
Data Index: 1123842 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3891. Min Act: -0.1700
Data Index: 6810676 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.4203. Min Act: -0.1700
Data Index: 7224847 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3891. Min Act: -0.1700
Data Index: 2063090 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3891. Min Act: -0.1700
Data Index: 6493137 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3891. Min Act: -0.1700
Data Index: 4553800 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3578. Min Act: -0.1700
Data Index: 4746881 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3578. Min Act: -0.1700
Data Index: 3818199 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3578. Min Act: -0.1700
Data Index: 3007107 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6079. Min Range: -4.6079
Max Act: 4.3266. Min Act: -0.1700
Data Index: 1566780 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19