Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6759. Min Act: -0.1700
Data Index: 5643725 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6672. Min Act: -0.1700
Data Index: 5430190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6498. Min Act: -0.1602
Data Index: 6683858 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6498. Min Act: -0.1700
Data Index: 3446969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6411. Min Act: -0.1688
Data Index: 6831384 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6411. Min Act: -0.1375
Data Index: 4017315 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6150. Min Act: -0.1685
Data Index: 184885 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6324. Min Act: -0.1700
Data Index: 7062296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6062. Min Act: -0.1700
Data Index: 1910810 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6150. Min Act: -0.1684
Data Index: 184881 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6150. Min Act: -0.1698
Data Index: 8532192 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6062. Min Act: -0.1700
Data Index: 8301810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6150. Min Act: -0.1700
Data Index: 8011222 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6150. Min Act: -0.1536
Data Index: 4111156 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.6062. Min Act: -0.1700
Data Index: 222947 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.5888. Min Act: -0.1650
Data Index: 4569356 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.5888. Min Act: -0.1700
Data Index: 4413567 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.5800. Min Act: -0.1652
Data Index: 4750537 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.5713. Min Act: -0.1694
Data Index: 8721478 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6759. Min Range: -1.6759
Max Act: 1.5713. Min Act: -0.1700
Data Index: 2167072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19