Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.9357. Min Act: -0.1700
Data Index: 8372128 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.6856. Min Act: -0.1700
Data Index: 5609265 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.6230. Min Act: -0.1700
Data Index: 8823850 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.5760. Min Act: -0.1700
Data Index: 226230 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.5604. Min Act: -0.1700
Data Index: 7770135 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.5604. Min Act: -0.1700
Data Index: 3040258 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4821. Min Act: -0.1700
Data Index: 3958910 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4194. Min Act: -0.1700
Data Index: 4960896 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4351. Min Act: -0.1700
Data Index: 8662987 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4037. Min Act: -0.1700
Data Index: 2878702 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4037. Min Act: -0.1700
Data Index: 3717666 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3880. Min Act: -0.1700
Data Index: 6402472 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.4037. Min Act: -0.1700
Data Index: 3348434 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3723. Min Act: -0.1700
Data Index: 3985674 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3567. Min Act: -0.1700
Data Index: 8251545 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3567. Min Act: -0.1700
Data Index: 5153708 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3567. Min Act: -0.1700
Data Index: 3459964 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3410. Min Act: -0.1700
Data Index: 1342723 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3410. Min Act: -0.1700
Data Index: 4999778 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9357. Min Range: -3.9357
Max Act: 3.3410. Min Act: -0.1700
Data Index: 5768247 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19