Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.6289. Min Act: -0.1700
Data Index: 6456393 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.3789. Min Act: -0.1700
Data Index: 3895129 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.2852. Min Act: -0.1700
Data Index: 4592065 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.2539. Min Act: -0.1700
Data Index: 4540187 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.1602. Min Act: -0.1700
Data Index: 6956035 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.1914. Min Act: -0.1700
Data Index: 6745999 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.0664. Min Act: -0.1700
Data Index: 5816490 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.0664. Min Act: -0.1700
Data Index: 7723465 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.0039. Min Act: -0.1700
Data Index: 2558289 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6289. Min Range: -6.6289
Max Act: 6.0039. Min Act: -0.1700
Data Index: 7601716 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9727. Min Act: -0.1700
Data Index: 5416511 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 7795582 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 47781 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9727. Min Act: -0.1700
Data Index: 994005 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9727. Min Act: -0.1700
Data Index: 2373633 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 7935000 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 6106445 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9102. Min Act: -0.1700
Data Index: 8104302 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 636527 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6289. Min Range: -6.6289
Max Act: 5.9414. Min Act: -0.1700
Data Index: 1519917 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19