Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.2318. Min Act: -0.1700
Data Index: 7832324 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1693. Min Act: -0.1700
Data Index: 837884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1693. Min Act: -0.1700
Data Index: 4539555 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1693. Min Act: -0.1685
Data Index: 4539533 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1380. Min Act: -0.1700
Data Index: 1820869 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1380. Min Act: -0.1700
Data Index: 3639385 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 4274137 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 2478553 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1695
Data Index: 1326501 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 1759002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 7371228 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 8310959 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 1327977 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 5147788 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 780724 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 5986775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.0755. Min Act: -0.1700
Data Index: 356831 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.1067. Min Act: -0.1700
Data Index: 5865469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.0755. Min Act: -0.1700
Data Index: 700388 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2318. Min Range: -4.2318
Max Act: 4.0755. Min Act: -0.1700
Data Index: 5894936 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19