Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.8625. Min Act: -0.1700
Data Index: 3811112 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.8000. Min Act: -0.1700
Data Index: 1980445 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.7531. Min Act: -0.1700
Data Index: 2172287 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.6905. Min Act: -0.1700
Data Index: 2097145 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.6749. Min Act: -0.1700
Data Index: 4181815 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.6436. Min Act: -0.1700
Data Index: 4906448 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.6279. Min Act: -0.1700
Data Index: 8125619 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5810. Min Act: -0.1700
Data Index: 8366421 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5966. Min Act: -0.1700
Data Index: 6286718 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5810. Min Act: -0.1700
Data Index: 7739446 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5810. Min Act: -0.1700
Data Index: 3412482 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5497. Min Act: -0.1700
Data Index: 6645741 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5497. Min Act: -0.1700
Data Index: 2663246 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5497. Min Act: -0.1700
Data Index: 5253276 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5497. Min Act: -0.1700
Data Index: 8790861 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5340. Min Act: -0.1700
Data Index: 1268396 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5340. Min Act: -0.1700
Data Index: 6230105 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5183. Min Act: -0.1700
Data Index: 7537049 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5183. Min Act: -0.1700
Data Index: 1212144 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8625. Min Range: -3.8625
Max Act: 3.5183. Min Act: -0.1700
Data Index: 1906672 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19