Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5187425 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.4136. Min Act: -0.1700
Data Index: 3967050 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3823. Min Act: -0.1700
Data Index: 4734280 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3511. Min Act: -0.1700
Data Index: 4730426 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3511. Min Act: -0.1700
Data Index: 4945714 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8348925 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.4136. Min Act: -0.1700
Data Index: 3329609 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.2886. Min Act: -0.1700
Data Index: 157659 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.3198. Min Act: -0.1700
Data Index: 1504712 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.2886. Min Act: -0.1700
Data Index: 8351069 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.2261. Min Act: -0.1700
Data Index: 672197 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.1948. Min Act: -0.1700
Data Index: 6353622 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.1948. Min Act: -0.1700
Data Index: 2998363 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.1636. Min Act: -0.1700
Data Index: 5706911 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.1323. Min Act: -0.1700
Data Index: 3972197 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.0698. Min Act: -0.1700
Data Index: 2686466 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.0698. Min Act: -0.1700
Data Index: 5760797 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.0073. Min Act: -0.1700
Data Index: 7124736 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.0073. Min Act: -0.1700
Data Index: 6780899 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4136. Min Range: -6.4136
Max Act: 6.0073. Min Act: -0.1700
Data Index: 7574544 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19