Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.6309. Min Act: -0.1700
Data Index: 4916241 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.3809. Min Act: -0.1700
Data Index: 6290076 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.3184. Min Act: -0.1700
Data Index: 4559338 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.1934. Min Act: -0.1700
Data Index: 7999515 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.1309. Min Act: -0.1700
Data Index: 8601336 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.1309. Min Act: -0.1700
Data Index: 183182 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.0684. Min Act: -0.1700
Data Index: 5748525 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.1309. Min Act: -0.1700
Data Index: 2552494 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.9434. Min Act: -0.1700
Data Index: 8559124 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.0059. Min Act: -0.1700
Data Index: 4842211 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6309. Min Range: -9.6309
Max Act: 9.0059. Min Act: -0.1700
Data Index: 5904912 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.9434. Min Act: -0.1700
Data Index: 2887406 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.8809. Min Act: -0.1700
Data Index: 7543343 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.8809. Min Act: -0.1700
Data Index: 6126898 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.8184. Min Act: -0.1700
Data Index: 5615604 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.8184. Min Act: -0.1700
Data Index: 860064 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.7559. Min Act: -0.1700
Data Index: 5331805 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.6934. Min Act: -0.1700
Data Index: 64481 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.6934. Min Act: -0.1700
Data Index: 860061 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6309. Min Range: -9.6309
Max Act: 8.6934. Min Act: -0.1700
Data Index: 742648 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19