Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.7513. Min Act: -0.1700
Data Index: 4426296 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.6646. Min Act: -0.1700
Data Index: 2212716 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.6472. Min Act: -0.1700
Data Index: 540367 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.6298. Min Act: -0.1700
Data Index: 2482722 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.6298. Min Act: -0.1700
Data Index: 6405800 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5949. Min Act: -0.1700
Data Index: 1373162 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.6124. Min Act: -0.1700
Data Index: 1642779 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5949. Min Act: -0.1700
Data Index: 3995853 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5774. Min Act: -0.1700
Data Index: 297839 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5774. Min Act: -0.1700
Data Index: 679473 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5774. Min Act: -0.1700
Data Index: 5493607 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5774. Min Act: -0.1700
Data Index: 321930 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5600. Min Act: -0.1700
Data Index: 5966325 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5774. Min Act: -0.1700
Data Index: 8371222 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5424. Min Act: -0.1700
Data Index: 4207623 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5249. Min Act: -0.1700
Data Index: 6405799 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5424. Min Act: -0.1700
Data Index: 4207624 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5249. Min Act: -0.1700
Data Index: 1991957 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5424. Min Act: -0.1700
Data Index: 3443810 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7513. Min Range: -1.7513
Max Act: 1.5424. Min Act: -0.1700
Data Index: 503494 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19