Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3662. Min Range: -5.3662
Max Act: 5.3662. Min Act: -0.1700
Data Index: 400731 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.9912. Min Act: -0.1700
Data Index: 3168228 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.9912. Min Act: -0.1700
Data Index: 1363382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.9287. Min Act: -0.1700
Data Index: 8374039 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.8349. Min Act: -0.1700
Data Index: 4348369 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.8037. Min Act: -0.1700
Data Index: 8386257 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 8468618 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 4296683 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 768220 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.8037. Min Act: -0.1700
Data Index: 4369692 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7724. Min Act: -0.1700
Data Index: 3077057 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7412. Min Act: -0.1700
Data Index: 8378912 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1593990 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6787. Min Act: -0.1700
Data Index: 2511294 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6787. Min Act: -0.1700
Data Index: 2544907 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6474. Min Act: -0.1700
Data Index: 4879660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6474. Min Act: -0.1700
Data Index: 3429590 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6162. Min Act: -0.1700
Data Index: 2471069 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6474. Min Act: -0.1700
Data Index: 5894852 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3662. Min Range: -5.3662
Max Act: 4.6162. Min Act: -0.1700
Data Index: 3361496 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19