Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6821. Min Range: -7.6821
Max Act: 7.6821. Min Act: -0.1700
Data Index: 1858711 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6821. Min Range: -7.6821
Max Act: 7.2133. Min Act: -0.1700
Data Index: 482337 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6821. Min Range: -7.6821
Max Act: 7.0571. Min Act: -0.1700
Data Index: 5149000 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6821. Min Range: -7.6821
Max Act: 7.0571. Min Act: -0.1700
Data Index: 5085239 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9633. Min Act: -0.1700
Data Index: 6875310 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9321. Min Act: -0.1700
Data Index: 999223 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9321. Min Act: -0.1700
Data Index: 4187728 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9321. Min Act: -0.1700
Data Index: 3807387 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9008. Min Act: -0.1700
Data Index: 3347914 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9008. Min Act: -0.1700
Data Index: 8392852 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.9008. Min Act: -0.1700
Data Index: 8465209 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8696. Min Act: -0.1700
Data Index: 6097526 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8383. Min Act: -0.1700
Data Index: 999463 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 8472274 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 4997935 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 6281609 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 5208143 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 2702592 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.7758. Min Act: -0.1700
Data Index: 7777700 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6821. Min Range: -7.6821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 6783621 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19