Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 571 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.5915. Min Act: -0.1700
Data Index: 4483478 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.4665. Min Act: -0.1700
Data Index: 6950852 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.4665. Min Act: -0.1700
Data Index: 275933 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.4040. Min Act: -0.1700
Data Index: 4483479 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.4040. Min Act: -0.1700
Data Index: 5593816 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.3415. Min Act: -0.1700
Data Index: 4483482 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.3415. Min Act: -0.1700
Data Index: 1251600 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.2790. Min Act: -0.1700
Data Index: 4929158 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 612951 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.2165. Min Act: -0.1700
Data Index: 1135272 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.2165. Min Act: -0.1700
Data Index: 6950853 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 2780113 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 275935 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 4483477 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 1251599 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.1540. Min Act: -0.1700
Data Index: 4483472 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.0915. Min Act: -0.1700
Data Index: 2320661 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.0915. Min Act: -0.1700
Data Index: 4483481 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.0915. Min Act: -0.1700
Data Index: 4483470 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5915. Min Range: -9.5915
Max Act: 9.0290. Min Act: -0.1700
Data Index: 3729277 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19