Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.4106. Min Act: -0.1700
Data Index: 2232139 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4362776 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.1918. Min Act: -0.1700
Data Index: 8389911 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.1606. Min Act: -0.1700
Data Index: 6264266 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.1606. Min Act: -0.1700
Data Index: 2275797 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.0981. Min Act: -0.1700
Data Index: 4661433 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.0043. Min Act: -0.1700
Data Index: 2613583 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4106. Min Range: -6.4106
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1677678 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9731. Min Act: -0.1700
Data Index: 7939419 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9418. Min Act: -0.1700
Data Index: 5404717 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9106. Min Act: -0.1700
Data Index: 8655724 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8793. Min Act: -0.1700
Data Index: 5582543 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9418. Min Act: -0.1700
Data Index: 1849387 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9106. Min Act: -0.1700
Data Index: 8458238 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.9106. Min Act: -0.1700
Data Index: 4502816 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8793. Min Act: -0.1700
Data Index: 5403211 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8793. Min Act: -0.1700
Data Index: 103094 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8481. Min Act: -0.1700
Data Index: 8331027 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8793. Min Act: -0.1700
Data Index: 8517634 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4106. Min Range: -6.4106
Max Act: 5.8793. Min Act: -0.1700
Data Index: 2019798 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19