Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3495. Min Act: -0.1700
Data Index: 4749701 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.3182. Min Act: -0.1700
Data Index: 3810089 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2870. Min Act: -0.1700
Data Index: 5378204 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.2557. Min Act: -0.1700
Data Index: 8377051 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0995. Min Act: -0.1700
Data Index: 5782522 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0682. Min Act: -0.1700
Data Index: 2012096 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0682. Min Act: -0.1700
Data Index: 7436849 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0057. Min Act: -0.1700
Data Index: 987620 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0057. Min Act: -0.1700
Data Index: 6009113 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3495. Min Range: -5.3495
Max Act: 5.0057. Min Act: -0.1700
Data Index: 976177 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9745. Min Act: -0.1700
Data Index: 5669939 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9745. Min Act: -0.1700
Data Index: 5373912 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9745. Min Act: -0.1700
Data Index: 2436970 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9745. Min Act: -0.1700
Data Index: 2838084 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9120. Min Act: -0.1700
Data Index: 5118575 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9120. Min Act: -0.1700
Data Index: 614431 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9120. Min Act: -0.1700
Data Index: 5555386 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9120. Min Act: -0.1700
Data Index: 2709440 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9432. Min Act: -0.1700
Data Index: 3927857 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3495. Min Range: -5.3495
Max Act: 4.9120. Min Act: -0.1700
Data Index: 8599983 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19