Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3836. Min Range: -6.3836
Max Act: 6.3836. Min Act: -0.1700
Data Index: 698135 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3836. Min Range: -6.3836
Max Act: 6.1023. Min Act: -0.1700
Data Index: 4056710 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3836. Min Range: -6.3836
Max Act: 6.1023. Min Act: -0.1700
Data Index: 3444544 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3836. Min Range: -6.3836
Max Act: 6.0398. Min Act: -0.1700
Data Index: 6210520 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3836. Min Range: -6.3836
Max Act: 6.0086. Min Act: -0.1700
Data Index: 3961850 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.9773. Min Act: -0.1700
Data Index: 7969055 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.9148. Min Act: -0.1700
Data Index: 3495538 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.9148. Min Act: -0.1700
Data Index: 2259080 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8668859 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7898. Min Act: -0.1700
Data Index: 604201 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7898. Min Act: -0.1700
Data Index: 5164486 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7898. Min Act: -0.1700
Data Index: 2068746 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 1342685 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 1306465 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 2184677 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 5979487 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 3992347 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 2654052 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7586. Min Act: -0.1700
Data Index: 1117557 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3836. Min Range: -6.3836
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6905509 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19