Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2189. Min Range: -6.2189
Max Act: 6.2189. Min Act: -0.1700
Data Index: 4352987 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2189. Min Range: -6.2189
Max Act: 6.1251. Min Act: -0.1700
Data Index: 1432186 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2189. Min Range: -6.2189
Max Act: 6.0626. Min Act: -0.1700
Data Index: 1432188 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2189. Min Range: -6.2189
Max Act: 6.0314. Min Act: -0.1700
Data Index: 7726979 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.9689. Min Act: -0.1700
Data Index: 1432187 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.9376. Min Act: -0.1700
Data Index: 1700068 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.9064. Min Act: -0.1700
Data Index: 6002812 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.9064. Min Act: -0.1700
Data Index: 7187010 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.8751. Min Act: -0.1700
Data Index: 864723 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.8439. Min Act: -0.1700
Data Index: 5146854 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.8126. Min Act: -0.1700
Data Index: 4482678 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7501. Min Act: -0.1700
Data Index: 8439044 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7814. Min Act: -0.1700
Data Index: 4482683 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7189. Min Act: -0.1700
Data Index: 1101834 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7501. Min Act: -0.1700
Data Index: 6850273 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7189. Min Act: -0.1700
Data Index: 89884 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.7189. Min Act: -0.1700
Data Index: 5505655 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.6876. Min Act: -0.1700
Data Index: 6710799 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.6876. Min Act: -0.1700
Data Index: 5772719 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2189. Min Range: -6.2189
Max Act: 5.6876. Min Act: -0.1700
Data Index: 1700067 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19