Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9964. Min Act: -0.1700
Data Index: 6421026 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9490. Min Act: -0.1700
Data Index: 1431246 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9331. Min Act: -0.1700
Data Index: 6613167 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9331. Min Act: -0.1700
Data Index: 2783184 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9173. Min Act: -0.1700
Data Index: 5384430 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9014. Min Act: -0.1700
Data Index: 7137986 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9014. Min Act: -0.1700
Data Index: 4016510 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9014. Min Act: -0.1700
Data Index: 1684401 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8697. Min Act: -0.1700
Data Index: 7661405 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8856. Min Act: -0.1700
Data Index: 6091348 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.9014. Min Act: -0.1700
Data Index: 8659039 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8697. Min Act: -0.1700
Data Index: 8764657 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8856. Min Act: -0.1700
Data Index: 8142471 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8697. Min Act: -0.1700
Data Index: 7031849 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8538. Min Act: -0.1700
Data Index: 867034 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8697. Min Act: -0.1700
Data Index: 8488456 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8538. Min Act: -0.1700
Data Index: 8177413 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8379. Min Act: -0.1700
Data Index: 6341234 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8538. Min Act: -0.1700
Data Index: 5383460 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9964. Min Range: -2.9964
Max Act: 2.8379. Min Act: -0.1700
Data Index: 7377697 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19