Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0913. Min Range: -4.0913
Max Act: 4.0913. Min Act: -0.1700
Data Index: 6130737 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9975. Min Act: -0.1700
Data Index: 101870 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0913. Min Range: -4.0913
Max Act: 4.0600. Min Act: -0.1700
Data Index: 2722502 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0913. Min Range: -4.0913
Max Act: 4.0288. Min Act: -0.1700
Data Index: 1492033 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9975. Min Act: -0.1700
Data Index: 1471076 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9662. Min Act: -0.1700
Data Index: 3463390 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9662. Min Act: -0.1700
Data Index: 4035256 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9662. Min Act: -0.1700
Data Index: 6579973 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9193. Min Act: -0.1700
Data Index: 6888836 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9193. Min Act: -0.1700
Data Index: 1570001 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9193. Min Act: -0.1700
Data Index: 5841582 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9037. Min Act: -0.1700
Data Index: 6442825 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9506. Min Act: -0.1700
Data Index: 1590493 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.8881. Min Act: -0.1700
Data Index: 400046 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9193. Min Act: -0.1700
Data Index: 7444569 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9193. Min Act: -0.1700
Data Index: 6629859 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9037. Min Act: -0.1700
Data Index: 1765103 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.8881. Min Act: -0.1700
Data Index: 5057961 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.8881. Min Act: -0.1700
Data Index: 1216092 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0913. Min Range: -4.0913
Max Act: 3.9037. Min Act: -0.1700
Data Index: 1431768 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19