Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.6294. Min Act: -0.1700
Data Index: 2042396 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.5669. Min Act: -0.1700
Data Index: 4664756 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.4107. Min Act: -0.1700
Data Index: 1912971 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.2857. Min Act: -0.1700
Data Index: 1997233 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.2544. Min Act: -0.1700
Data Index: 2178318 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.2232. Min Act: -0.1700
Data Index: 3712749 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1607. Min Act: -0.1700
Data Index: 1159498 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1607. Min Act: -0.1700
Data Index: 1040376 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1919. Min Act: -0.1700
Data Index: 5998911 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1294. Min Act: -0.1700
Data Index: 2305172 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1294. Min Act: -0.1700
Data Index: 225172 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.1294. Min Act: -0.1700
Data Index: 1643956 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 6203385 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0669. Min Act: -0.1700
Data Index: 4494002 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 3730230 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 689532 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0669. Min Act: -0.1700
Data Index: 1027941 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 3033530 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0669. Min Act: -0.1700
Data Index: 5049048 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6294. Min Range: -7.6294
Max Act: 7.0669. Min Act: -0.1700
Data Index: 2963530 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19