Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0904. Min Range: -1.0904
Max Act: 1.0904. Min Act: -0.1700
Data Index: 989407 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0904. Min Range: -1.0904
Max Act: 1.0555. Min Act: -0.1688
Data Index: 6187341 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0904. Min Range: -1.0904
Max Act: 1.0119. Min Act: -0.1700
Data Index: 4865074 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0904. Min Range: -1.0904
Max Act: 1.0119. Min Act: -0.1700
Data Index: 4796518 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9859. Min Act: -0.1700
Data Index: 1270725 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0904. Min Range: -1.0904
Max Act: 1.0032. Min Act: -0.1700
Data Index: 3740014 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9859. Min Act: -0.1700
Data Index: 5909819 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9772. Min Act: -0.1700
Data Index: 2568169 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9686. Min Act: -0.1700
Data Index: 1407881 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9513. Min Act: -0.1700
Data Index: 2117076 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9513. Min Act: -0.1700
Data Index: 1117930 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9341. Min Act: -0.1700
Data Index: 6366149 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9255. Min Act: -0.1700
Data Index: 1058794 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9169. Min Act: -0.1700
Data Index: 6563214 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9169. Min Act: -0.1700
Data Index: 4645845 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9169. Min Act: -0.1700
Data Index: 2765376 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9255. Min Act: -0.1700
Data Index: 709612 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9169. Min Act: -0.1700
Data Index: 4084669 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.9169. Min Act: -0.1700
Data Index: 7721712 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0904. Min Range: -1.0904
Max Act: 0.8912. Min Act: -0.1700
Data Index: 937408 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19