Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.7485. Min Act: -0.1700
Data Index: 1061010 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6548. Min Act: -0.1700
Data Index: 8091697 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6548. Min Act: -0.1700
Data Index: 8280559 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 7097385 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 4478581 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 4491525 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 8099210 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 8410505 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 6020936 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.6235. Min Act: -0.1700
Data Index: 5902673 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 982100 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 761613 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 1693980 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 6390400 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5297. Min Act: -0.1699
Data Index: 5697182 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 8727443 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5922. Min Act: -0.1700
Data Index: 3949656 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 502847 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 1354704 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7485. Min Range: -4.7485
Max Act: 4.5610. Min Act: -0.1700
Data Index: 4478582 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19