Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5789. Min Act: -0.1700
Data Index: 1595523 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4227. Min Act: -0.1700
Data Index: 6456015 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4539. Min Act: -0.1700
Data Index: 876539 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4227. Min Act: -0.1700
Data Index: 4018960 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3914. Min Act: -0.1700
Data Index: 4667382 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 1815445 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3289. Min Act: -0.1700
Data Index: 5077276 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2977. Min Act: -0.1700
Data Index: 176566 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3289. Min Act: -0.1700
Data Index: 3232120 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3289. Min Act: -0.1700
Data Index: 4582702 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2977. Min Act: -0.1700
Data Index: 8284767 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3289. Min Act: -0.1700
Data Index: 3576876 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7499264 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2664. Min Act: -0.1700
Data Index: 7578582 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2664. Min Act: -0.1700
Data Index: 2320896 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2977. Min Act: -0.1700
Data Index: 7614195 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2664. Min Act: -0.1700
Data Index: 8074448 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2664. Min Act: -0.1700
Data Index: 6654727 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2664. Min Act: -0.1700
Data Index: 4390901 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.2352. Min Act: -0.1700
Data Index: 594235 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19