Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.3623. Min Act: -0.1700
Data Index: 605709 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.3311. Min Act: -0.1700
Data Index: 1932821 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.1748. Min Act: -0.1700
Data Index: 7630320 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.1748. Min Act: -0.1700
Data Index: 6756624 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.1436. Min Act: -0.1700
Data Index: 5637686 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.1123. Min Act: -0.1700
Data Index: 6788647 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0811. Min Act: -0.1700
Data Index: 5041139 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0811. Min Act: -0.1700
Data Index: 5983373 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 2104045 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 4311245 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 636082 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 76821 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0811. Min Act: -0.1700
Data Index: 3461013 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 1300924 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 5776945 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0498. Min Act: -0.1700
Data Index: 4876494 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0186. Min Act: -0.1700
Data Index: 7228754 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0186. Min Act: -0.1700
Data Index: 2911093 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0186. Min Act: -0.1700
Data Index: 1498523 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3623. Min Range: -5.3623
Max Act: 5.0186. Min Act: -0.1700
Data Index: 2019342 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19